Hugging Face's logo

Spaces:
meval
/
multilingual-chatbot-arena-leaderboard
Running

App Files Community
eduagarcia commited on
Commit
f290486
•
1 Parent(s): a52f768

Cleanup files

Browse files
Files changed (42) hide show
  1. elo_results_20230508.pkl +0 -3
  2. elo_results_20230522.pkl +0 -3
  3. elo_results_20230619.pkl +0 -3
  4. elo_results_20230717.pkl +0 -3
  5. elo_results_20230802.pkl +0 -3
  6. elo_results_20230905.pkl +0 -3
  7. elo_results_20231002.pkl +0 -3
  8. elo_results_20231108.pkl +0 -3
  9. elo_results_20231116.pkl +0 -3
  10. elo_results_20231206.pkl +0 -3
  11. elo_results_20231215.pkl +0 -3
  12. elo_results_20231220.pkl +0 -3
  13. elo_results_20240109.pkl +0 -3
  14. elo_results_20240118.pkl +0 -3
  15. elo_results_20240125.pkl +0 -3
  16. elo_results_20240202.pkl +0 -3
  17. elo_results_20240215.pkl +0 -3
  18. elo_results_20240305.pkl +0 -3
  19. elo_results_20240307.pkl +0 -3
  20. elo_results_20240313.pkl +0 -3
  21. elo_results_20240326.pkl +0 -3
  22. elo_results_20240329.pkl +0 -3
  23. leaderboard_table_20230619.csv +0 -32
  24. leaderboard_table_20230717.csv +0 -39
  25. leaderboard_table_20230802.csv +0 -41
  26. leaderboard_table_20230905.csv +0 -44
  27. leaderboard_table_20231002.csv +0 -45
  28. leaderboard_table_20231108.csv +0 -50
  29. leaderboard_table_20231116.csv +0 -52
  30. leaderboard_table_20231206.csv +0 -62
  31. leaderboard_table_20231215.csv +0 -65
  32. leaderboard_table_20231220.csv +0 -66
  33. leaderboard_table_20240109.csv +0 -69
  34. leaderboard_table_20240118.csv +0 -70
  35. leaderboard_table_20240125.csv +0 -72
  36. leaderboard_table_20240202.csv +0 -73
  37. leaderboard_table_20240215.csv +0 -79
  38. leaderboard_table_20240305.csv +0 -84
  39. leaderboard_table_20240307.csv +0 -88
  40. leaderboard_table_20240313.csv +0 -88
  41. leaderboard_table_20240326.csv +0 -90
  42. leaderboard_table_20240329.csv +0 -91
elo_results_20230508.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:50dbde9cbbadd4939233edf2a25ad2ee345e0ce5af4e310000846bf67a410f5d
3
- size 26558
 
 
 
 
elo_results_20230522.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c4bb2b7b36f5d84251105a4ccacdad0e9a2d1028f1d7382bdfb2af4acfe18488
3
- size 29557
 
 
 
 
elo_results_20230619.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6fb496441c181c6f8fabd0f832fbba0c75a622511f1c9916c13535976fa6ff6
3
- size 32184
 
 
 
 
elo_results_20230717.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae6feeba2538ea2593da1971df50eaa436ab114ba3d91be39de3cf5c692d293f
3
- size 34065
 
 
 
 
elo_results_20230802.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2918cd54236776fd0f05ae1ad858297159fb46298b32af19f2b1ee4310baa40e
3
- size 37078
 
 
 
 
elo_results_20230905.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2bdbeeb5e205b9dfb105b4be02931591b8759bca7bb36d32189c53d8dc8d4453
3
- size 40474
 
 
 
 
elo_results_20231002.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5b3ed8668fd1321e28623fc434269274a70ed011b67513cb3ce785d3309f458
3
- size 38147
 
 
 
 
elo_results_20231108.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:da91b104eb39b9adcb9020ca24fc3946ffaaacbabf9ddbf86ca1cf2d54e203e6
3
- size 39003
 
 
 
 
elo_results_20231116.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0072e5bdcee16d0d2db6ae0a6c7c450e0c4ce66188dc3e3a65d6ee24e8391152
3
- size 39363
 
 
 
 
elo_results_20231206.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2dfb49266d1f7316b674bdd7bbd28eba6517a77ebdd9253707b3ae96ab6df0d
3
- size 42785
 
 
 
 
elo_results_20231215.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0848b15e0a15df023703734666cbd59a50a621b865aa66aefd0b7e066eccbd6d
3
- size 43790
 
 
 
 
elo_results_20231220.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd896f0f288e634fd7b349d14b08427c2591a5a099ce1e8366c154ef625ca5d5
3
- size 44317
 
 
 
 
elo_results_20240109.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a334a1a5000f62dd9491d6fb2c7b136cce3fd37647ffec0e9c0c084919783ea
3
- size 264666
 
 
 
 
elo_results_20240118.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e11075b63da01d65998db00115787a11d3f949e1d758ccf7f934b53d9814590
3
- size 268916
 
 
 
 
elo_results_20240125.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:61ce75a347e0350f865e4c5f4a4c7d9c13ba82650ab3393f58b781d40b0068f2
3
- size 183519
 
 
 
 
elo_results_20240202.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ba78fc7a83db4017649da3961abec3ccd94255fa0aa39b928dc8472d896127e
3
- size 95932
 
 
 
 
elo_results_20240215.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:69e83158197af8b7135d0a1f418c2ec01fc3760a58243836f2f8096693ed7c8e
3
- size 102175
 
 
 
 
elo_results_20240305.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d7c44b600ca85d3843c50b9669d22155d66e2d8dd5d8402da20c4c9951b3f9f
3
- size 107550
 
 
 
 
elo_results_20240307.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd51f95d6c872755bfe782b9a4ccc74a44fe57428776341a315ae1cabf611cd8
3
- size 111751
 
 
 
 
elo_results_20240313.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e9dcbec26330eb7243e83b9ddebff1f65a92007dec325a38af09cad65cdb3ce
3
- size 112351
 
 
 
 
elo_results_20240326.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a155fb5ee3dc95d67cf0a177982fc02a0fa1affaf11f80b2d43d19ac5925a385
3
- size 114797
 
 
 
 
elo_results_20240329.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f4c037f68c9ddbf27b70b1cb333ca37bf70ff9a3cddad7a93cd62bca709cd77
3
- size 115776
 
 
 
 
leaderboard_table_20230619.csv DELETED
@@ -1,32 +0,0 @@
1
- Model,MT-bench (win rate %),MT-bench (score),Arena Elo rating,MMLU,License,Link
2
- GPT-4,69.38%,8.99,1227,0.864,Proprietary,https://openai.com/research/gpt-4
3
- GPT-3.5-turbo,-,7.94,1130,0.700,Proprietary,https://openai.com/blog/chatgpt
4
- Claude-v1,46.88%,7.90,1178,0.756,Proprietary,https://www.anthropic.com/index/introducing-claude
5
- Claude-instant-v1,40.00%,7.85,1156,0.613,Proprietary,https://www.anthropic.com/index/introducing-claude
6
- Vicuna-33B,43.75%,7.12,-,0.592,Non-commercial,https://huggingface.co/lmsys/vicuna-33b-v1.3
7
- WizardLM-30B,23.13%,7.01,-,0.587,Non-commercial,https://huggingface.co/WizardLM/WizardLM-30B-V1.0
8
- Guanaco-33B,26.25%,6.53,1065,0.576,Non-commercial,https://huggingface.co/timdettmers/guanaco-33b-merged
9
- Tulu-30B,18.13%,6.43,-,0.581,Non-commercial,https://huggingface.co/allenai/tulu-30b
10
- Guanaco-65B,23.75%,6.41,-,0.621,Non-commercial,https://huggingface.co/timdettmers/guanaco-65b-merged
11
- OpenAssistant-LLaMA-30B,14.38%,6.41,-,0.560,Non-commercial,https://huggingface.co/OpenAssistant/oasst-sft-6-llama-30b-xor
12
- PaLM-Chat-Bison-001,11.25%,6.40,1038,-,Proprietary,https://cloud.google.com/vertex-ai/docs/generative-ai/learn/models#foundation_models
13
- Vicuna-13B,20.63%,6.39,1061,0.521,Non-commercial,https://huggingface.co/lmsys/vicuna-13b-v1.3
14
- MPT-30B-chat,18.13%,6.39,-,0.504,CC-BY-NC-SA-4.0,https://huggingface.co/mosaicml/mpt-30b-chat
15
- WizardLM-13B,16.88%,6.35,1048,0.523,Non-commercial,https://huggingface.co/WizardLM/WizardLM-13B-V1.0
16
- Vicuna-7B,18.75%,6.00,1008,0.471,Non-commercial,https://huggingface.co/lmsys/vicuna-7b-v1.3
17
- Baize-v2-13B,13.13%,5.75,-,0.489,Non-commercial,https://huggingface.co/project-baize/baize-v2-13b
18
- Nous-Hermes-13B,7.50%,5.51,-,0.493,Non-commercial,https://huggingface.co/NousResearch/Nous-Hermes-13b
19
- MPT-7B-Chat,6.25%,5.42,956,0.320,CC-BY-NC-SA-4.0,https://huggingface.co/mosaicml/mpt-7b-chat
20
- GPT4All-13B-Snoozy,8.75%,5.41,986,0.430,Non-commercial,https://huggingface.co/nomic-ai/gpt4all-13b-snoozy
21
- Koala-13B,6.25%,5.35,992,0.447,Non-commercial,https://bair.berkeley.edu/blog/2023/04/03/koala/
22
- MPT-30B-Instruct,4.38%,5.22,-,0.478,CC-BY-SA 3.0,https://huggingface.co/mosaicml/mpt-30b-instruct
23
- Falcon-40B-Instruct,6.25%,5.17,-,0.547,Apache 2.0,https://huggingface.co/tiiuae/falcon-40b-instruct
24
- H2O-Oasst-OpenLLaMA-13B,11.88%,4.63,-,0.428,Apache 2.0,https://huggingface.co/h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-13b
25
- Alpaca-13B,5.00%,4.53,930,0.481,Non-commercial,https://crfm.stanford.edu/2023/03/13/alpaca.html
26
- ChatGLM-6B,3.75%,4.50,905,0.361,Non-commercial,https://huggingface.co/THUDM/chatglm-6b
27
- OpenAssistant-Pythia-12B,5.00%,4.32,924,0.270,Apache 2.0,https://huggingface.co/OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5
28
- RWKV-4-Raven-14B,3.75%,3.98,950,0.256,Apache 2.0,https://huggingface.co/BlinkDL/rwkv-4-raven
29
- Dolly-V2-12B,3.13%,3.28,850,0.257,MIT,https://huggingface.co/databricks/dolly-v2-12b
30
- FastChat-T5-3B,3.13%,3.04,897,0.477,Apache 2.0,https://huggingface.co/lmsys/fastchat-t5-3b-v1.0
31
- StableLM-Tuned-Alpha-7B,0.63%,2.75,871,0.244,CC-BY-NC-SA-4.0,https://huggingface.co/stabilityai/stablelm-tuned-alpha-7b
32
- LLaMA-13B,1.88%,2.61,826,0.470,Non-commercial,https://arxiv.org/abs/2302.13971
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
leaderboard_table_20230717.csv DELETED
@@ -1,39 +0,0 @@
1
- Model,MT-bench (score),Arena Elo rating,MMLU,License,Link
2
- GPT-4,8.99,1211,0.864,Proprietary,https://openai.com/research/gpt-4
3
- Claude-2,8.06,-,0.785,Proprietary,https://www.anthropic.com/index/claude-2
4
- GPT-3.5-turbo,7.94,1124,0.700,Proprietary,https://openai.com/blog/chatgpt
5
- Claude-v1,7.90,1169,0.770,Proprietary,https://www.anthropic.com/index/introducing-claude
6
- Claude-instant-v1,7.85,1145,0.734,Proprietary,https://www.anthropic.com/index/introducing-claude
7
- Vicuna-33B,7.12,1096,0.592,Non-commercial,https://huggingface.co/lmsys/vicuna-33b-v1.3
8
- WizardLM-30B,7.01,-,0.587,Non-commercial,https://huggingface.co/WizardLM/WizardLM-30B-V1.0
9
- Llama-2-70b-chat,6.86,-,-,Llama 2 Community,https://huggingface.co/meta-llama/Llama-2-70b-hf
10
- WizardLM-13B-v1.1,6.76,-,-,Non-commercial,https://huggingface.co/WizardLM/WizardLM-13B-V1.1
11
- Llama-2-13b-chat,6.65,-,-,Llama 2 Community,https://huggingface.co/meta-llama/Llama-2-13b-hf
12
- Guanaco-33B,6.53,1044,0.576,Non-commercial,https://huggingface.co/timdettmers/guanaco-33b-merged
13
- Tulu-30B,6.43,-,0.581,Non-commercial,https://huggingface.co/allenai/tulu-30b
14
- Guanaco-65B,6.41,-,0.621,Non-commercial,https://huggingface.co/timdettmers/guanaco-65b-merged
15
- OpenAssistant-LLaMA-30B,6.41,-,0.560,Non-commercial,https://huggingface.co/OpenAssistant/oasst-sft-6-llama-30b-xor
16
- PaLM-Chat-Bison-001,6.40,1019,-,Proprietary,https://cloud.google.com/vertex-ai/docs/generative-ai/learn/models#foundation_models
17
- Vicuna-13B,6.39,1055,0.521,Non-commercial,https://huggingface.co/lmsys/vicuna-13b-v1.3
18
- MPT-30B-chat,6.39,1049,0.504,CC-BY-NC-SA-4.0,https://huggingface.co/mosaicml/mpt-30b-chat
19
- WizardLM-13B,6.35,1043,0.523,Non-commercial,https://huggingface.co/WizardLM/WizardLM-13B-V1.0
20
- Llama-2-7b-chat,6.27,-,-,Llama 2 Community,https://huggingface.co/meta-llama/Llama-2-7b-chat-hf
21
- Vicuna-7B,6.00,1006,0.471,Non-commercial,https://huggingface.co/lmsys/vicuna-7b-v1.3
22
- Baize-v2-13B,5.75,-,0.489,Non-commercial,https://huggingface.co/project-baize/baize-v2-13b
23
- XGen-7B-8K-Inst,5.55,-,-,Non-commercial,https://huggingface.co/Salesforce/xgen-7b-8k-inst
24
- Nous-Hermes-13B,5.51,-,0.493,Non-commercial,https://huggingface.co/NousResearch/Nous-Hermes-13b
25
- MPT-7B-Chat,5.42,951,0.320,CC-BY-NC-SA-4.0,https://huggingface.co/mosaicml/mpt-7b-chat
26
- GPT4All-13B-Snoozy,5.41,971,0.430,Non-commercial,https://huggingface.co/nomic-ai/gpt4all-13b-snoozy
27
- Koala-13B,5.35,987,0.447,Non-commercial,https://bair.berkeley.edu/blog/2023/04/03/koala/
28
- MPT-30B-Instruct,5.22,-,0.478,CC-BY-SA 3.0,https://huggingface.co/mosaicml/mpt-30b-instruct
29
- Falcon-40B-Instruct,5.17,-,0.547,Apache 2.0,https://huggingface.co/tiiuae/falcon-40b-instruct
30
- ChatGLM2-6B,4.96,-,-,Apache-2.0,https://huggingface.co/THUDM/chatglm2-6b
31
- H2O-Oasst-OpenLLaMA-13B,4.63,-,0.428,Apache 2.0,https://huggingface.co/h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-13b
32
- Alpaca-13B,4.53,926,0.481,Non-commercial,https://crfm.stanford.edu/2023/03/13/alpaca.html
33
- ChatGLM-6B,4.50,904,0.361,Non-commercial,https://huggingface.co/THUDM/chatglm-6b
34
- OpenAssistant-Pythia-12B,4.32,919,0.270,Apache 2.0,https://huggingface.co/OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5
35
- RWKV-4-Raven-14B,3.98,946,0.256,Apache 2.0,https://huggingface.co/BlinkDL/rwkv-4-raven
36
- Dolly-V2-12B,3.28,846,0.257,MIT,https://huggingface.co/databricks/dolly-v2-12b
37
- FastChat-T5-3B,3.04,897,0.477,Apache 2.0,https://huggingface.co/lmsys/fastchat-t5-3b-v1.0
38
- StableLM-Tuned-Alpha-7B,2.75,867,0.244,CC-BY-NC-SA-4.0,https://huggingface.co/stabilityai/stablelm-tuned-alpha-7b
39
- LLaMA-13B,2.61,821,0.470,Non-commercial,https://arxiv.org/abs/2302.13971
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
leaderboard_table_20230802.csv DELETED
@@ -1,41 +0,0 @@
1
- Model,MT-bench (score),Arena Elo rating,MMLU,License,Link
2
- GPT-4,8.99,1206,0.864,Proprietary,https://openai.com/research/gpt-4
3
- Claude-2,8.06,1135,0.785,Proprietary,https://www.anthropic.com/index/claude-2
4
- GPT-3.5-turbo,7.94,1122,0.700,Proprietary,https://openai.com/blog/chatgpt
5
- Claude-1,7.90,1166,0.770,Proprietary,https://www.anthropic.com/index/introducing-claude
6
- Claude-instant-1,7.85,1138,0.734,Proprietary,https://www.anthropic.com/index/introducing-claude
7
- Vicuna-33B,7.12,1096,0.592,Non-commercial,https://huggingface.co/lmsys/vicuna-33b-v1.3
8
- WizardLM-30B,7.01,-,0.587,Non-commercial,https://huggingface.co/WizardLM/WizardLM-30B-V1.0
9
- Vicuna-13B-16k,6.92,-,0.545,Llama 2 Community,https://huggingface.co/lmsys/vicuna-13b-v1.5-16k
10
- Llama-2-70b-chat,6.86,-,0.630,Llama 2 Community,https://huggingface.co/meta-llama/Llama-2-70b-chat-hf
11
- WizardLM-13B-v1.1,6.76,1040,0.500,Non-commercial,https://huggingface.co/WizardLM/WizardLM-13B-V1.1
12
- Llama-2-13b-chat,6.65,987,0.536,Llama 2 Community,https://huggingface.co/meta-llama/Llama-2-13b-chat-hf
13
- Vicuna-13B,6.57,1051,0.558,Llama 2 Community,https://huggingface.co/lmsys/vicuna-13b-v1.5
14
- Guanaco-33B,6.53,1038,0.576,Non-commercial,https://huggingface.co/timdettmers/guanaco-33b-merged
15
- Tulu-30B,6.43,-,0.581,Non-commercial,https://huggingface.co/allenai/tulu-30b
16
- Guanaco-65B,6.41,-,0.621,Non-commercial,https://huggingface.co/timdettmers/guanaco-65b-merged
17
- OpenAssistant-LLaMA-30B,6.41,-,0.560,Non-commercial,https://huggingface.co/OpenAssistant/oasst-sft-6-llama-30b-xor
18
- PaLM-Chat-Bison-001,6.40,1015,-,Proprietary,https://cloud.google.com/vertex-ai/docs/generative-ai/learn/models#foundation_models
19
- MPT-30B-chat,6.39,1046,0.504,CC-BY-NC-SA-4.0,https://huggingface.co/mosaicml/mpt-30b-chat
20
- WizardLM-13B,6.35,-,0.523,Non-commercial,https://huggingface.co/WizardLM/WizardLM-13B-V1.0
21
- Llama-2-7b-chat,6.27,961,0.458,Llama 2 Community,https://huggingface.co/meta-llama/Llama-2-7b-chat-hf
22
- Vicuna-7B-16k,6.22,-,0.485,Llama 2 Community,https://huggingface.co/lmsys/vicuna-7b-v1.5-16k
23
- Vicuna-7B,6.17,1006,0.498,Llama 2 Community,https://huggingface.co/lmsys/vicuna-7b-v1.5
24
- Baize-v2-13B,5.75,-,0.489,Non-commercial,https://huggingface.co/project-baize/baize-v2-13b
25
- XGen-7B-8K-Inst,5.55,-,0.421,Non-commercial,https://huggingface.co/Salesforce/xgen-7b-8k-inst
26
- Nous-Hermes-13B,5.51,-,0.493,Non-commercial,https://huggingface.co/NousResearch/Nous-Hermes-13b
27
- MPT-7B-Chat,5.42,947,0.320,CC-BY-NC-SA-4.0,https://huggingface.co/mosaicml/mpt-7b-chat
28
- GPT4All-13B-Snoozy,5.41,967,0.430,Non-commercial,https://huggingface.co/nomic-ai/gpt4all-13b-snoozy
29
- Koala-13B,5.35,983,0.447,Non-commercial,https://bair.berkeley.edu/blog/2023/04/03/koala/
30
- MPT-30B-Instruct,5.22,-,0.478,CC-BY-SA 3.0,https://huggingface.co/mosaicml/mpt-30b-instruct
31
- Falcon-40B-Instruct,5.17,-,0.547,Apache 2.0,https://huggingface.co/tiiuae/falcon-40b-instruct
32
- ChatGLM2-6B,4.96,-,0.455,Apache-2.0,https://huggingface.co/THUDM/chatglm2-6b
33
- H2O-Oasst-OpenLLaMA-13B,4.63,-,0.428,Apache 2.0,https://huggingface.co/h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-13b
34
- Alpaca-13B,4.53,923,0.481,Non-commercial,https://crfm.stanford.edu/2023/03/13/alpaca.html
35
- ChatGLM-6B,4.50,900,0.361,Non-commercial,https://huggingface.co/THUDM/chatglm-6b
36
- OpenAssistant-Pythia-12B,4.32,915,0.270,Apache 2.0,https://huggingface.co/OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5
37
- RWKV-4-Raven-14B,3.98,943,0.256,Apache 2.0,https://huggingface.co/BlinkDL/rwkv-4-raven
38
- Dolly-V2-12B,3.28,842,0.257,MIT,https://huggingface.co/databricks/dolly-v2-12b
39
- FastChat-T5-3B,3.04,892,0.477,Apache 2.0,https://huggingface.co/lmsys/fastchat-t5-3b-v1.0
40
- StableLM-Tuned-Alpha-7B,2.75,863,0.244,CC-BY-NC-SA-4.0,https://huggingface.co/stabilityai/stablelm-tuned-alpha-7b
41
- LLaMA-13B,2.61,817,0.470,Non-commercial,https://arxiv.org/abs/2302.13971
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
leaderboard_table_20230905.csv DELETED
@@ -1,44 +0,0 @@
1
- Model,MT-bench (score),Arena Elo rating,MMLU,License,Link
2
- CodeLlama-34B-instruct,-,1032,-,Llama 2 Community,https://huggingface.co/codellama/CodeLlama-34b-Instruct-hf
3
- GPT-4,8.99,1193,0.864,Proprietary,https://openai.com/research/gpt-4
4
- Claude-2,8.06,1134,0.785,Proprietary,https://www.anthropic.com/index/claude-2
5
- GPT-3.5-turbo,7.94,1118,0.700,Proprietary,https://openai.com/blog/chatgpt
6
- Claude-1,7.90,1161,0.770,Proprietary,https://www.anthropic.com/index/introducing-claude
7
- Claude-instant-1,7.85,1130,0.734,Proprietary,https://www.anthropic.com/index/introducing-claude
8
- WizardLM-70b-v1.0,7.71,-,0.637,Llama 2 Community,https://huggingface.co/WizardLM/WizardLM-70B-V1.0
9
- WizardLM-13b-v1.2,7.20,1046,0.527,Llama 2 Community,https://huggingface.co/WizardLM/WizardLM-13B-V1.2
10
- Vicuna-33B,7.12,1097,0.592,Non-commercial,https://huggingface.co/lmsys/vicuna-33b-v1.3
11
- WizardLM-30B,7.01,-,0.587,Non-commercial,https://huggingface.co/WizardLM/WizardLM-30B-V1.0
12
- Vicuna-13B-16k,6.92,-,0.545,Llama 2 Community,https://huggingface.co/lmsys/vicuna-13b-v1.5-16k
13
- Llama-2-70b-chat,6.86,1060,0.630,Llama 2 Community,https://huggingface.co/meta-llama/Llama-2-70b-chat-hf
14
- WizardLM-13B-v1.1,6.76,-,0.500,Non-commercial,https://huggingface.co/WizardLM/WizardLM-13B-V1.1
15
- Llama-2-13b-chat,6.65,999,0.536,Llama 2 Community,https://huggingface.co/meta-llama/Llama-2-13b-chat-hf
16
- Vicuna-13B,6.57,1046,0.558,Llama 2 Community,https://huggingface.co/lmsys/vicuna-13b-v1.5
17
- Guanaco-33B,6.53,1036,0.576,Non-commercial,https://huggingface.co/timdettmers/guanaco-33b-merged
18
- Tulu-30B,6.43,-,0.581,Non-commercial,https://huggingface.co/allenai/tulu-30b
19
- Guanaco-65B,6.41,-,0.621,Non-commercial,https://huggingface.co/timdettmers/guanaco-65b-merged
20
- OpenAssistant-LLaMA-30B,6.41,-,0.560,Non-commercial,https://huggingface.co/OpenAssistant/oasst-sft-6-llama-30b-xor
21
- PaLM-Chat-Bison-001,6.40,1008,-,Proprietary,https://cloud.google.com/vertex-ai/docs/generative-ai/learn/models#foundation_models
22
- MPT-30B-chat,6.39,1043,0.504,CC-BY-NC-SA-4.0,https://huggingface.co/mosaicml/mpt-30b-chat
23
- WizardLM-13B-v1.0,6.35,-,0.523,Non-commercial,https://huggingface.co/WizardLM/WizardLM-13B-V1.0
24
- Llama-2-7b-chat,6.27,979,0.458,Llama 2 Community,https://huggingface.co/meta-llama/Llama-2-7b-chat-hf
25
- Vicuna-7B-16k,6.22,-,0.485,Llama 2 Community,https://huggingface.co/lmsys/vicuna-7b-v1.5-16k
26
- Vicuna-7B,6.17,1003,0.498,Llama 2 Community,https://huggingface.co/lmsys/vicuna-7b-v1.5
27
- Baize-v2-13B,5.75,-,0.489,Non-commercial,https://huggingface.co/project-baize/baize-v2-13b
28
- XGen-7B-8K-Inst,5.55,-,0.421,Non-commercial,https://huggingface.co/Salesforce/xgen-7b-8k-inst
29
- Nous-Hermes-13B,5.51,-,0.493,Non-commercial,https://huggingface.co/NousResearch/Nous-Hermes-13b
30
- MPT-7B-Chat,5.42,943,0.320,CC-BY-NC-SA-4.0,https://huggingface.co/mosaicml/mpt-7b-chat
31
- GPT4All-13B-Snoozy,5.41,964,0.430,Non-commercial,https://huggingface.co/nomic-ai/gpt4all-13b-snoozy
32
- Koala-13B,5.35,979,0.447,Non-commercial,https://bair.berkeley.edu/blog/2023/04/03/koala/
33
- MPT-30B-Instruct,5.22,-,0.478,CC-BY-SA 3.0,https://huggingface.co/mosaicml/mpt-30b-instruct
34
- Falcon-40B-Instruct,5.17,-,0.547,Apache 2.0,https://huggingface.co/tiiuae/falcon-40b-instruct
35
- ChatGLM2-6B,4.96,965,0.455,Apache-2.0,https://huggingface.co/THUDM/chatglm2-6b
36
- H2O-Oasst-OpenLLaMA-13B,4.63,-,0.428,Apache 2.0,https://huggingface.co/h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-13b
37
- Alpaca-13B,4.53,919,0.481,Non-commercial,https://crfm.stanford.edu/2023/03/13/alpaca.html
38
- ChatGLM-6B,4.50,896,0.361,Non-commercial,https://huggingface.co/THUDM/chatglm-6b
39
- OpenAssistant-Pythia-12B,4.32,911,0.270,Apache 2.0,https://huggingface.co/OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5
40
- RWKV-4-Raven-14B,3.98,939,0.256,Apache 2.0,https://huggingface.co/BlinkDL/rwkv-4-raven
41
- Dolly-V2-12B,3.28,838,0.257,MIT,https://huggingface.co/databricks/dolly-v2-12b
42
- FastChat-T5-3B,3.04,888,0.477,Apache 2.0,https://huggingface.co/lmsys/fastchat-t5-3b-v1.0
43
- StableLM-Tuned-Alpha-7B,2.75,859,0.244,CC-BY-NC-SA-4.0,https://huggingface.co/stabilityai/stablelm-tuned-alpha-7b
44
- LLaMA-13B,2.61,814,0.470,Non-commercial,https://arxiv.org/abs/2302.13971
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
leaderboard_table_20231002.csv DELETED
@@ -1,45 +0,0 @@
1
- Model,MT-bench (score),Arena Elo rating,MMLU,License,Link
2
- WizardLM-30B,7.01,-,0.587,Non-commercial,https://huggingface.co/WizardLM/WizardLM-30B-V1.0
3
- Vicuna-13B-16k,6.92,-,0.545,Llama 2 Community,https://huggingface.co/lmsys/vicuna-13b-v1.5-16k
4
- WizardLM-13B-v1.1,6.76,-,0.500,Non-commercial,https://huggingface.co/WizardLM/WizardLM-13B-V1.1
5
- Tulu-30B,6.43,-,0.581,Non-commercial,https://huggingface.co/allenai/tulu-30b
6
- Guanaco-65B,6.41,-,0.621,Non-commercial,https://huggingface.co/timdettmers/guanaco-65b-merged
7
- OpenAssistant-LLaMA-30B,6.41,-,0.560,Non-commercial,https://huggingface.co/OpenAssistant/oasst-sft-6-llama-30b-xor
8
- WizardLM-13B-v1.0,6.35,-,0.523,Non-commercial,https://huggingface.co/WizardLM/WizardLM-13B-V1.0
9
- Vicuna-7B-16k,6.22,-,0.485,Llama 2 Community,https://huggingface.co/lmsys/vicuna-7b-v1.5-16k
10
- Baize-v2-13B,5.75,-,0.489,Non-commercial,https://huggingface.co/project-baize/baize-v2-13b
11
- XGen-7B-8K-Inst,5.55,-,0.421,Non-commercial,https://huggingface.co/Salesforce/xgen-7b-8k-inst
12
- Nous-Hermes-13B,5.51,-,0.493,Non-commercial,https://huggingface.co/NousResearch/Nous-Hermes-13b
13
- MPT-30B-Instruct,5.22,-,0.478,CC-BY-SA 3.0,https://huggingface.co/mosaicml/mpt-30b-instruct
14
- Falcon-40B-Instruct,5.17,-,0.547,Apache 2.0,https://huggingface.co/tiiuae/falcon-40b-instruct
15
- H2O-Oasst-OpenLLaMA-13B,4.63,-,0.428,Apache 2.0,https://huggingface.co/h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-13b
16
- GPT-4,8.99,1181,0.864,Proprietary,https://openai.com/research/gpt-4
17
- Claude-1,7.90,1155,0.770,Proprietary,https://www.anthropic.com/index/introducing-claude
18
- Claude-2,8.06,1134,0.785,Proprietary,https://www.anthropic.com/index/claude-2
19
- Claude-instant-1,7.85,1119,0.734,Proprietary,https://www.anthropic.com/index/introducing-claude
20
- GPT-3.5-turbo,7.94,1115,0.700,Proprietary,https://openai.com/blog/chatgpt
21
- WizardLM-70b-v1.0,7.71,1099,0.637,Llama 2 Community,https://huggingface.co/WizardLM/WizardLM-70B-V1.0
22
- Vicuna-33B,7.12,1092,0.592,Non-commercial,https://huggingface.co/lmsys/vicuna-33b-v1.3
23
- Llama-2-70b-chat,6.86,1051,0.630,Llama 2 Community,https://huggingface.co/meta-llama/Llama-2-70b-chat-hf
24
- WizardLM-13b-v1.2,7.20,1047,0.527,Llama 2 Community,https://huggingface.co/WizardLM/WizardLM-13B-V1.2
25
- Vicuna-13B,6.57,1041,0.558,Llama 2 Community,https://huggingface.co/lmsys/vicuna-13b-v1.5
26
- MPT-30B-chat,6.39,1039,0.504,CC-BY-NC-SA-4.0,https://huggingface.co/mosaicml/mpt-30b-chat
27
- Guanaco-33B,6.53,1031,0.576,Non-commercial,https://huggingface.co/timdettmers/guanaco-33b-merged
28
- CodeLlama-34B-instruct,-,1031,0.537,Llama 2 Community,https://huggingface.co/codellama/CodeLlama-34b-Instruct-hf
29
- Mistral-7B-Instruct-v0.1,6.84,1031,-,Apache 2.0,https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1
30
- Llama-2-13b-chat,6.65,1012,0.536,Llama 2 Community,https://huggingface.co/meta-llama/Llama-2-13b-chat-hf
31
- PaLM-Chat-Bison-001,6.40,1002,-,Proprietary,https://cloud.google.com/vertex-ai/docs/generative-ai/learn/models#foundation_models
32
- Vicuna-7B,6.17,997,0.498,Llama 2 Community,https://huggingface.co/lmsys/vicuna-7b-v1.5
33
- Llama-2-7b-chat,6.27,985,0.458,Llama 2 Community,https://huggingface.co/meta-llama/Llama-2-7b-chat-hf
34
- Koala-13B,5.35,973,0.447,Non-commercial,https://bair.berkeley.edu/blog/2023/04/03/koala/
35
- GPT4All-13B-Snoozy,5.41,959,0.430,Non-commercial,https://huggingface.co/nomic-ai/gpt4all-13b-snoozy
36
- ChatGLM2-6B,4.96,945,0.455,Apache-2.0,https://huggingface.co/THUDM/chatglm2-6b
37
- MPT-7B-Chat,5.42,938,0.320,CC-BY-NC-SA-4.0,https://huggingface.co/mosaicml/mpt-7b-chat
38
- RWKV-4-Raven-14B,3.98,933,0.256,Apache 2.0,https://huggingface.co/BlinkDL/rwkv-4-raven
39
- Alpaca-13B,4.53,914,0.481,Non-commercial,https://crfm.stanford.edu/2023/03/13/alpaca.html
40
- OpenAssistant-Pythia-12B,4.32,905,0.270,Apache 2.0,https://huggingface.co/OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5
41
- ChatGLM-6B,4.50,892,0.361,Non-commercial,https://huggingface.co/THUDM/chatglm-6b
42
- FastChat-T5-3B,3.04,884,0.477,Apache 2.0,https://huggingface.co/lmsys/fastchat-t5-3b-v1.0
43
- StableLM-Tuned-Alpha-7B,2.75,853,0.244,CC-BY-NC-SA-4.0,https://huggingface.co/stabilityai/stablelm-tuned-alpha-7b
44
- Dolly-V2-12B,3.28,832,0.257,MIT,https://huggingface.co/databricks/dolly-v2-12b
45
- LLaMA-13B,2.61,809,0.470,Non-commercial,https://arxiv.org/abs/2302.13971
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
leaderboard_table_20231108.csv DELETED
@@ -1,50 +0,0 @@
1
- Model,MT-bench (score),Arena Elo rating,MMLU,License,Link
2
- WizardLM-30B,7.01,-,0.587,Non-commercial,https://huggingface.co/WizardLM/WizardLM-30B-V1.0
3
- Vicuna-13B-16k,6.92,-,0.545,Llama 2 Community,https://huggingface.co/lmsys/vicuna-13b-v1.5-16k
4
- WizardLM-13B-v1.1,6.76,-,0.500,Non-commercial,https://huggingface.co/WizardLM/WizardLM-13B-V1.1
5
- Tulu-30B,6.43,-,0.581,Non-commercial,https://huggingface.co/allenai/tulu-30b
6
- Guanaco-65B,6.41,-,0.621,Non-commercial,https://huggingface.co/timdettmers/guanaco-65b-merged
7
- OpenAssistant-LLaMA-30B,6.41,-,0.560,Non-commercial,https://huggingface.co/OpenAssistant/oasst-sft-6-llama-30b-xor
8
- WizardLM-13B-v1.0,6.35,-,0.523,Non-commercial,https://huggingface.co/WizardLM/WizardLM-13B-V1.0
9
- Vicuna-7B-16k,6.22,-,0.485,Llama 2 Community,https://huggingface.co/lmsys/vicuna-7b-v1.5-16k
10
- Baize-v2-13B,5.75,-,0.489,Non-commercial,https://huggingface.co/project-baize/baize-v2-13b
11
- XGen-7B-8K-Inst,5.55,-,0.421,Non-commercial,https://huggingface.co/Salesforce/xgen-7b-8k-inst
12
- Nous-Hermes-13B,5.51,-,0.493,Non-commercial,https://huggingface.co/NousResearch/Nous-Hermes-13b
13
- MPT-30B-Instruct,5.22,-,0.478,CC-BY-SA 3.0,https://huggingface.co/mosaicml/mpt-30b-instruct
14
- Falcon-40B-Instruct,5.17,-,0.547,Apache 2.0,https://huggingface.co/tiiuae/falcon-40b-instruct
15
- H2O-Oasst-OpenLLaMA-13B,4.63,-,0.428,Apache 2.0,https://huggingface.co/h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-13b
16
- GPT-4,8.99,1169,0.864,Proprietary,https://openai.com/research/gpt-4
17
- Claude-1,7.90,1153,0.770,Proprietary,https://www.anthropic.com/index/introducing-claude
18
- Claude-2,8.06,1128,0.785,Proprietary,https://www.anthropic.com/index/claude-2
19
- Claude-instant-1,7.85,1109,0.734,Proprietary,https://www.anthropic.com/index/introducing-claude
20
- GPT-3.5-turbo,7.94,1109,0.700,Proprietary,https://openai.com/blog/chatgpt
21
- WizardLM-70b-v1.0,7.71,1096,0.637,Llama 2 Community,https://huggingface.co/WizardLM/WizardLM-70B-V1.0
22
- Vicuna-33B,7.12,1095,0.592,Non-commercial,https://huggingface.co/lmsys/vicuna-33b-v1.3
23
- Llama-2-70b-chat,6.86,1072,0.630,Llama 2 Community,https://huggingface.co/meta-llama/Llama-2-70b-chat-hf
24
- OpenChat-3.5,7.81,1066,0.643,Apache-2.0,https://huggingface.co/openchat/openchat_3.5
25
- WizardLM-13b-v1.2,7.20,1051,0.527,Llama 2 Community,https://huggingface.co/WizardLM/WizardLM-13B-V1.2
26
- zephyr-7b-beta,7.34,1044,0.614,MIT,https://huggingface.co/HuggingFaceH4/zephyr-7b-beta
27
- MPT-30B-chat,6.39,1038,0.504,CC-BY-NC-SA-4.0,https://huggingface.co/mosaicml/mpt-30b-chat
28
- Vicuna-13B,6.57,1037,0.558,Llama 2 Community,https://huggingface.co/lmsys/vicuna-13b-v1.5
29
- QWen-Chat-14B,6.96,1031,0.665,Qianwen LICENSE,https://huggingface.co/Qwen/Qwen-14B-Chat
30
- falcon-180b-chat,-,1031,0.680,Falcon-180B TII License,https://huggingface.co/tiiuae/falcon-180B-chat
31
- zephyr-7b-alpha,6.88,1028,-,MIT,https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha
32
- CodeLlama-34B-instruct,-,1028,0.537,Llama 2 Community,https://huggingface.co/codellama/CodeLlama-34b-Instruct-hf
33
- Guanaco-33B,6.53,1027,0.576,Non-commercial,https://huggingface.co/timdettmers/guanaco-33b-merged
34
- Llama-2-13b-chat,6.65,1026,0.536,Llama 2 Community,https://huggingface.co/meta-llama/Llama-2-13b-chat-hf
35
- Mistral-7B-Instruct-v0.1,6.84,1013,0.554,Apache 2.0,https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1
36
- Llama-2-7b-chat,6.27,1008,0.458,Llama 2 Community,https://huggingface.co/meta-llama/Llama-2-7b-chat-hf
37
- Vicuna-7B,6.17,1000,0.498,Llama 2 Community,https://huggingface.co/lmsys/vicuna-7b-v1.5
38
- PaLM-Chat-Bison-001,6.40,996,-,Proprietary,https://cloud.google.com/vertex-ai/docs/generative-ai/learn/models#foundation_models
39
- Koala-13B,5.35,960,0.447,Non-commercial,https://bair.berkeley.edu/blog/2023/04/03/koala/
40
- GPT4All-13B-Snoozy,5.41,932,0.430,Non-commercial,https://huggingface.co/nomic-ai/gpt4all-13b-snoozy
41
- MPT-7B-Chat,5.42,925,0.320,CC-BY-NC-SA-4.0,https://huggingface.co/mosaicml/mpt-7b-chat
42
- ChatGLM2-6B,4.96,922,0.455,Apache-2.0,https://huggingface.co/THUDM/chatglm2-6b
43
- RWKV-4-Raven-14B,3.98,919,0.256,Apache 2.0,https://huggingface.co/BlinkDL/rwkv-4-raven
44
- Alpaca-13B,4.53,898,0.481,Non-commercial,https://crfm.stanford.edu/2023/03/13/alpaca.html
45
- OpenAssistant-Pythia-12B,4.32,890,0.270,Apache 2.0,https://huggingface.co/OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5
46
- ChatGLM-6B,4.50,877,0.361,Non-commercial,https://huggingface.co/THUDM/chatglm-6b
47
- FastChat-T5-3B,3.04,869,0.477,Apache 2.0,https://huggingface.co/lmsys/fastchat-t5-3b-v1.0
48
- StableLM-Tuned-Alpha-7B,2.75,839,0.244,CC-BY-NC-SA-4.0,https://huggingface.co/stabilityai/stablelm-tuned-alpha-7b
49
- Dolly-V2-12B,3.28,817,0.257,MIT,https://huggingface.co/databricks/dolly-v2-12b
50
- LLaMA-13B,2.61,795,0.470,Non-commercial,https://arxiv.org/abs/2302.13971
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
leaderboard_table_20231116.csv DELETED
@@ -1,52 +0,0 @@
1
- Model,MT-bench (score),Arena Elo rating,MMLU,License,Link
2
- WizardLM-30B,7.01,-,0.587,Non-commercial,https://huggingface.co/WizardLM/WizardLM-30B-V1.0
3
- Vicuna-13B-16k,6.92,-,0.545,Llama 2 Community,https://huggingface.co/lmsys/vicuna-13b-v1.5-16k
4
- WizardLM-13B-v1.1,6.76,-,0.500,Non-commercial,https://huggingface.co/WizardLM/WizardLM-13B-V1.1
5
- Tulu-30B,6.43,-,0.581,Non-commercial,https://huggingface.co/allenai/tulu-30b
6
- Guanaco-65B,6.41,-,0.621,Non-commercial,https://huggingface.co/timdettmers/guanaco-65b-merged
7
- OpenAssistant-LLaMA-30B,6.41,-,0.560,Non-commercial,https://huggingface.co/OpenAssistant/oasst-sft-6-llama-30b-xor
8
- WizardLM-13B-v1.0,6.35,-,0.523,Non-commercial,https://huggingface.co/WizardLM/WizardLM-13B-V1.0
9
- Vicuna-7B-16k,6.22,-,0.485,Llama 2 Community,https://huggingface.co/lmsys/vicuna-7b-v1.5-16k
10
- Baize-v2-13B,5.75,-,0.489,Non-commercial,https://huggingface.co/project-baize/baize-v2-13b
11
- XGen-7B-8K-Inst,5.55,-,0.421,Non-commercial,https://huggingface.co/Salesforce/xgen-7b-8k-inst
12
- Nous-Hermes-13B,5.51,-,0.493,Non-commercial,https://huggingface.co/NousResearch/Nous-Hermes-13b
13
- MPT-30B-Instruct,5.22,-,0.478,CC-BY-SA 3.0,https://huggingface.co/mosaicml/mpt-30b-instruct
14
- Falcon-40B-Instruct,5.17,-,0.547,Apache 2.0,https://huggingface.co/tiiuae/falcon-40b-instruct
15
- H2O-Oasst-OpenLLaMA-13B,4.63,-,0.428,Apache 2.0,https://huggingface.co/h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-13b
16
- GPT-4-Turbo,9.32,1210,-,Proprietary,https://openai.com/blog/new-models-and-developer-products-announced-at-devday
17
- GPT-4,8.99,1159,0.864,Proprietary,https://openai.com/research/gpt-4
18
- Claude-1,7.90,1146,0.770,Proprietary,https://www.anthropic.com/index/introducing-claude
19
- Claude-2,8.06,1125,0.785,Proprietary,https://www.anthropic.com/index/claude-2
20
- Claude-instant-1,7.85,1106,0.734,Proprietary,https://www.anthropic.com/index/introducing-claude
21
- GPT-3.5-turbo,7.94,1103,0.700,Proprietary,https://openai.com/blog/chatgpt
22
- WizardLM-70b-v1.0,7.71,1093,0.637,Llama 2 Community,https://huggingface.co/WizardLM/WizardLM-70B-V1.0
23
- Vicuna-33B,7.12,1090,0.592,Non-commercial,https://huggingface.co/lmsys/vicuna-33b-v1.3
24
- Llama-2-70b-chat,6.86,1065,0.630,Llama 2 Community,https://huggingface.co/meta-llama/Llama-2-70b-chat-hf
25
- OpenChat-3.5,7.81,1070,0.643,Apache-2.0,https://huggingface.co/openchat/openchat_3.5
26
- WizardLM-13b-v1.2,7.20,1047,0.527,Llama 2 Community,https://huggingface.co/WizardLM/WizardLM-13B-V1.2
27
- zephyr-7b-beta,7.34,1042,0.614,MIT,https://huggingface.co/HuggingFaceH4/zephyr-7b-beta
28
- MPT-30B-chat,6.39,1031,0.504,CC-BY-NC-SA-4.0,https://huggingface.co/mosaicml/mpt-30b-chat
29
- Vicuna-13B,6.57,1031,0.558,Llama 2 Community,https://huggingface.co/lmsys/vicuna-13b-v1.5
30
- QWen-Chat-14B,6.96,1030,0.665,Qianwen LICENSE,https://huggingface.co/Qwen/Qwen-14B-Chat
31
- falcon-180b-chat,-,1024,0.680,Falcon-180B TII License,https://huggingface.co/tiiuae/falcon-180B-chat
32
- zephyr-7b-alpha,6.88,1024,-,MIT,https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha
33
- CodeLlama-34B-instruct,-,1022,0.537,Llama 2 Community,https://huggingface.co/codellama/CodeLlama-34b-Instruct-hf
34
- Guanaco-33B,6.53,1021,0.576,Non-commercial,https://huggingface.co/timdettmers/guanaco-33b-merged
35
- Llama-2-13b-chat,6.65,1021,0.536,Llama 2 Community,https://huggingface.co/meta-llama/Llama-2-13b-chat-hf
36
- Mistral-7B-Instruct-v0.1,6.84,1008,0.554,Apache 2.0,https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1
37
- Llama-2-7b-chat,6.27,1001,0.458,Llama 2 Community,https://huggingface.co/meta-llama/Llama-2-7b-chat-hf
38
- Vicuna-7B,6.17,994,0.498,Llama 2 Community,https://huggingface.co/lmsys/vicuna-7b-v1.5
39
- PaLM-Chat-Bison-001,6.40,991,-,Proprietary,https://cloud.google.com/vertex-ai/docs/generative-ai/learn/models#foundation_models
40
- Koala-13B,5.35,955,0.447,Non-commercial,https://bair.berkeley.edu/blog/2023/04/03/koala/
41
- ChatGLM3-6B,-,970,-,Apache-2.0,https://huggingface.co/THUDM/chatglm3-6b
42
- GPT4All-13B-Snoozy,5.41,925,0.430,Non-commercial,https://huggingface.co/nomic-ai/gpt4all-13b-snoozy
43
- MPT-7B-Chat,5.42,918,0.320,CC-BY-NC-SA-4.0,https://huggingface.co/mosaicml/mpt-7b-chat
44
- ChatGLM2-6B,4.96,918,0.455,Apache-2.0,https://huggingface.co/THUDM/chatglm2-6b
45
- RWKV-4-Raven-14B,3.98,915,0.256,Apache 2.0,https://huggingface.co/BlinkDL/rwkv-4-raven
46
- Alpaca-13B,4.53,893,0.481,Non-commercial,https://crfm.stanford.edu/2023/03/13/alpaca.html
47
- OpenAssistant-Pythia-12B,4.32,884,0.270,Apache 2.0,https://huggingface.co/OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5
48
- ChatGLM-6B,4.50,871,0.361,Non-commercial,https://huggingface.co/THUDM/chatglm-6b
49
- FastChat-T5-3B,3.04,863,0.477,Apache 2.0,https://huggingface.co/lmsys/fastchat-t5-3b-v1.0
50
- StableLM-Tuned-Alpha-7B,2.75,833,0.244,CC-BY-NC-SA-4.0,https://huggingface.co/stabilityai/stablelm-tuned-alpha-7b
51
- Dolly-V2-12B,3.28,810,0.257,MIT,https://huggingface.co/databricks/dolly-v2-12b
52
- LLaMA-13B,2.61,789,0.470,Non-commercial,https://arxiv.org/abs/2302.13971
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
leaderboard_table_20231206.csv DELETED
@@ -1,62 +0,0 @@
1
- Model,MT-bench (score),Arena Elo rating,MMLU,License,Link
2
- WizardLM-30B,7.01,-,0.587,Non-commercial,https://huggingface.co/WizardLM/WizardLM-30B-V1.0
3
- Vicuna-13B-16k,6.92,-,0.545,Llama 2 Community,https://huggingface.co/lmsys/vicuna-13b-v1.5-16k
4
- WizardLM-13B-v1.1,6.76,-,0.500,Non-commercial,https://huggingface.co/WizardLM/WizardLM-13B-V1.1
5
- Tulu-30B,6.43,-,0.581,Non-commercial,https://huggingface.co/allenai/tulu-30b
6
- Guanaco-65B,6.41,-,0.621,Non-commercial,https://huggingface.co/timdettmers/guanaco-65b-merged
7
- OpenAssistant-LLaMA-30B,6.41,-,0.560,Non-commercial,https://huggingface.co/OpenAssistant/oasst-sft-6-llama-30b-xor
8
- WizardLM-13B-v1.0,6.35,-,0.523,Non-commercial,https://huggingface.co/WizardLM/WizardLM-13B-V1.0
9
- Vicuna-7B-16k,6.22,-,0.485,Llama 2 Community,https://huggingface.co/lmsys/vicuna-7b-v1.5-16k
10
- Baize-v2-13B,5.75,-,0.489,Non-commercial,https://huggingface.co/project-baize/baize-v2-13b
11
- XGen-7B-8K-Inst,5.55,-,0.421,Non-commercial,https://huggingface.co/Salesforce/xgen-7b-8k-inst
12
- Nous-Hermes-13B,5.51,-,0.493,Non-commercial,https://huggingface.co/NousResearch/Nous-Hermes-13b
13
- MPT-30B-Instruct,5.22,-,0.478,CC-BY-SA 3.0,https://huggingface.co/mosaicml/mpt-30b-instruct
14
- Falcon-40B-Instruct,5.17,-,0.547,Apache 2.0,https://huggingface.co/tiiuae/falcon-40b-instruct
15
- H2O-Oasst-OpenLLaMA-13B,4.63,-,0.428,Apache 2.0,https://huggingface.co/h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-13b
16
- GPT-4-Turbo,9.32,1217,-,Proprietary,https://openai.com/blog/new-models-and-developer-products-announced-at-devday
17
- GPT-4-0314,8.96,1201,0.864,Proprietary,https://openai.com/research/gpt-4
18
- Claude-1,7.90,1153,0.770,Proprietary,https://www.anthropic.com/index/introducing-claude
19
- GPT-4-0613,9.18,1152,-,Proprietary,https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo
20
- Claude-2.0,8.06,1127,0.785,Proprietary,https://www.anthropic.com/index/claude-2
21
- Claude-2.1,8.18,1118,-,Proprietary,https://www.anthropic.com/index/claude-2-1
22
- GPT-3.5-turbo-0613,8.39,1112,-,Proprietary,https://platform.openai.com/docs/models/gpt-3-5
23
- Claude-instant-1,7.85,1109,0.734,Proprietary,https://www.anthropic.com/index/introducing-claude
24
- GPT-3.5-turbo-0314,7.94,1105,0.700,Proprietary,https://platform.openai.com/docs/models/gpt-3-5
25
- Tulu-2-DPO-70B,7.89,1105,-,AI2 ImpACT Low-risk,https://huggingface.co/allenai/tulu-2-dpo-70b
26
- Yi-34B-chat,-,1102,0.735,Yi License,https://huggingface.co/01-ai/Yi-34B-Chat
27
- WizardLM-70b-v1.0,7.71,1097,0.637,Llama 2 Community,https://huggingface.co/WizardLM/WizardLM-70B-V1.0
28
- Vicuna-33B,7.12,1093,0.592,Non-commercial,https://huggingface.co/lmsys/vicuna-33b-v1.3
29
- Starling-lm-7b-alpha,8.09,1083,0.639,CC-BY-NC-4.0,https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha
30
- pplx-70b-online,-,1080,-,Proprietary,https://blog.perplexity.ai/blog/introducing-pplx-online-llms
31
- OpenChat-3.5,7.81,1077,0.643,Apache-2.0,https://huggingface.co/openchat/openchat_3.5
32
- OpenHermes-2.5-Mistral-7b,-,1075,-,Apache-2.0,https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B
33
- GPT-3.5-Turbo-1106,8.32,1074,-,Proprietary,https://platform.openai.com/docs/models/gpt-3-5
34
- Llama-2-70b-chat,6.86,1069,0.630,Llama 2 Community,https://huggingface.co/meta-llama/Llama-2-70b-chat-hf
35
- WizardLM-13b-v1.2,7.20,1053,0.527,Llama 2 Community,https://huggingface.co/WizardLM/WizardLM-13B-V1.2
36
- Zephyr-7b-beta,7.34,1045,0.614,MIT,https://huggingface.co/HuggingFaceH4/zephyr-7b-beta
37
- MPT-30B-chat,6.39,1039,0.504,CC-BY-NC-SA-4.0,https://huggingface.co/mosaicml/mpt-30b-chat
38
- Vicuna-13B,6.57,1039,0.558,Llama 2 Community,https://huggingface.co/lmsys/vicuna-13b-v1.5
39
- QWen-Chat-14B,6.96,1039,0.665,Qianwen LICENSE,https://huggingface.co/Qwen/Qwen-14B-Chat
40
- Zephyr-7b-alpha,6.88,1034,-,MIT,https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha
41
- CodeLlama-34B-instruct,-,1032,0.537,Llama 2 Community,https://huggingface.co/codellama/CodeLlama-34b-Instruct-hf
42
- falcon-180b-chat,-,1031,0.680,Falcon-180B TII License,https://huggingface.co/tiiuae/falcon-180B-chat
43
- Guanaco-33B,6.53,1029,0.576,Non-commercial,https://huggingface.co/timdettmers/guanaco-33b-merged
44
- Llama-2-13b-chat,6.65,1027,0.536,Llama 2 Community,https://huggingface.co/meta-llama/Llama-2-13b-chat-hf
45
- Mistral-7B-Instruct-v0.1,6.84,1018,0.554,Apache 2.0,https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1
46
- pplx-7b-online,-,1017,-,Proprietary,https://blog.perplexity.ai/blog/introducing-pplx-online-llms
47
- Llama-2-7b-chat,6.27,1009,0.458,Llama 2 Community,https://huggingface.co/meta-llama/Llama-2-7b-chat-hf
48
- Vicuna-7B,6.17,1002,0.498,Llama 2 Community,https://huggingface.co/lmsys/vicuna-7b-v1.5
49
- PaLM-Chat-Bison-001,6.40,1000,-,Proprietary,https://cloud.google.com/vertex-ai/docs/generative-ai/learn/models#foundation_models
50
- Koala-13B,5.35,966,0.447,Non-commercial,https://bair.berkeley.edu/blog/2023/04/03/koala/
51
- ChatGLM3-6B,-,958,-,Apache-2.0,https://huggingface.co/THUDM/chatglm3-6b
52
- GPT4All-13B-Snoozy,5.41,936,0.430,Non-commercial,https://huggingface.co/nomic-ai/gpt4all-13b-snoozy
53
- MPT-7B-Chat,5.42,930,0.320,CC-BY-NC-SA-4.0,https://huggingface.co/mosaicml/mpt-7b-chat
54
- ChatGLM2-6B,4.96,924,0.455,Apache-2.0,https://huggingface.co/THUDM/chatglm2-6b
55
- RWKV-4-Raven-14B,3.98,924,0.256,Apache 2.0,https://huggingface.co/BlinkDL/rwkv-4-raven
56
- Alpaca-13B,4.53,904,0.481,Non-commercial,https://crfm.stanford.edu/2023/03/13/alpaca.html
57
- OpenAssistant-Pythia-12B,4.32,896,0.270,Apache 2.0,https://huggingface.co/OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5
58
- ChatGLM-6B,4.50,882,0.361,Non-commercial,https://huggingface.co/THUDM/chatglm-6b
59
- FastChat-T5-3B,3.04,873,0.477,Apache 2.0,https://huggingface.co/lmsys/fastchat-t5-3b-v1.0
60
- StableLM-Tuned-Alpha-7B,2.75,845,0.244,CC-BY-NC-SA-4.0,https://huggingface.co/stabilityai/stablelm-tuned-alpha-7b
61
- Dolly-V2-12B,3.28,822,0.257,MIT,https://huggingface.co/databricks/dolly-v2-12b
62
- LLaMA-13B,2.61,800,0.470,Non-commercial,https://arxiv.org/abs/2302.13971
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
leaderboard_table_20231215.csv DELETED
@@ -1,65 +0,0 @@
1
- Model,MT-bench (score),Arena Elo rating,MMLU,License,Link
2
- WizardLM-30B,7.01,-,0.587,Non-commercial,https://huggingface.co/WizardLM/WizardLM-30B-V1.0
3
- Vicuna-13B-16k,6.92,-,0.545,Llama 2 Community,https://huggingface.co/lmsys/vicuna-13b-v1.5-16k
4
- WizardLM-13B-v1.1,6.76,-,0.500,Non-commercial,https://huggingface.co/WizardLM/WizardLM-13B-V1.1
5
- Tulu-30B,6.43,-,0.581,Non-commercial,https://huggingface.co/allenai/tulu-30b
6
- Guanaco-65B,6.41,-,0.621,Non-commercial,https://huggingface.co/timdettmers/guanaco-65b-merged
7
- OpenAssistant-LLaMA-30B,6.41,-,0.560,Non-commercial,https://huggingface.co/OpenAssistant/oasst-sft-6-llama-30b-xor
8
- WizardLM-13B-v1.0,6.35,-,0.523,Non-commercial,https://huggingface.co/WizardLM/WizardLM-13B-V1.0
9
- Vicuna-7B-16k,6.22,-,0.485,Llama 2 Community,https://huggingface.co/lmsys/vicuna-7b-v1.5-16k
10
- Baize-v2-13B,5.75,-,0.489,Non-commercial,https://huggingface.co/project-baize/baize-v2-13b
11
- XGen-7B-8K-Inst,5.55,-,0.421,Non-commercial,https://huggingface.co/Salesforce/xgen-7b-8k-inst
12
- Nous-Hermes-13B,5.51,-,0.493,Non-commercial,https://huggingface.co/NousResearch/Nous-Hermes-13b
13
- MPT-30B-Instruct,5.22,-,0.478,CC-BY-SA 3.0,https://huggingface.co/mosaicml/mpt-30b-instruct
14
- Falcon-40B-Instruct,5.17,-,0.547,Apache 2.0,https://huggingface.co/tiiuae/falcon-40b-instruct
15
- H2O-Oasst-OpenLLaMA-13B,4.63,-,0.428,Apache 2.0,https://huggingface.co/h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-13b
16
- GPT-4-Turbo,9.32,1233,-,Proprietary,https://openai.com/blog/new-models-and-developer-products-announced-at-devday
17
- GPT-4-0314,8.96,1191,0.864,Proprietary,https://openai.com/research/gpt-4
18
- Claude-1,7.90,1151,0.770,Proprietary,https://www.anthropic.com/index/introducing-claude
19
- GPT-4-0613,9.18,1157,-,Proprietary,https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo
20
- Claude-2.0,8.06,1130,0.785,Proprietary,https://www.anthropic.com/index/claude-2
21
- Claude-2.1,8.18,1120,-,Proprietary,https://www.anthropic.com/index/claude-2-1
22
- GPT-3.5-Turbo-0613,8.39,1116,-,Proprietary,https://platform.openai.com/docs/models/gpt-3-5
23
- Mixtral-8x7b-Instruct-v0.1,8.30,1116,0.706,Apache 2.0,https://mistral.ai/news/mixtral-of-experts/
24
- Claude-Instant-1,7.85,1110,0.734,Proprietary,https://www.anthropic.com/index/introducing-claude
25
- GPT-3.5-Turbo-0314,7.94,1105,0.700,Proprietary,https://platform.openai.com/docs/models/gpt-3-5
26
- Tulu-2-DPO-70B,7.89,1110,-,AI2 ImpACT Low-risk,https://huggingface.co/allenai/tulu-2-dpo-70b
27
- Yi-34B-Chat,-,1109,0.735,Yi License,https://huggingface.co/01-ai/Yi-34B-Chat
28
- Gemini Pro,-,1106,0.718,Proprietary,https://blog.google/technology/ai/gemini-api-developers-cloud/
29
- WizardLM-70B-v1.0,7.71,1102,0.637,Llama 2 Community,https://huggingface.co/WizardLM/WizardLM-70B-V1.0
30
- Vicuna-33B,7.12,1096,0.592,Non-commercial,https://huggingface.co/lmsys/vicuna-33b-v1.3
31
- Starling-LM-7B-alpha,8.09,1088,0.639,CC-BY-NC-4.0,https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha
32
- pplx-70b-online,-,1075,-,Proprietary,https://blog.perplexity.ai/blog/introducing-pplx-online-llms
33
- OpenChat-3.5,7.81,1077,0.643,Apache-2.0,https://huggingface.co/openchat/openchat_3.5
34
- OpenHermes-2.5-Mistral-7b,-,1072,-,Apache-2.0,https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B
35
- GPT-3.5-Turbo-1106,8.32,1077,-,Proprietary,https://platform.openai.com/docs/models/gpt-3-5
36
- Llama-2-70b-chat,6.86,1074,0.630,Llama 2 Community,https://huggingface.co/meta-llama/Llama-2-70b-chat-hf
37
- Dolphin-2.2.1-Mistral-7B,-,1072,-,Apache-2.0,https://huggingface.co/ehartford/dolphin-2.2.1-mistral-7b
38
- WizardLM-13b-v1.2,7.20,1056,0.527,Llama 2 Community,https://huggingface.co/WizardLM/WizardLM-13B-V1.2
39
- Zephyr-7b-beta,7.34,1049,0.614,MIT,https://huggingface.co/HuggingFaceH4/zephyr-7b-beta
40
- MPT-30B-chat,6.39,1041,0.504,CC-BY-NC-SA-4.0,https://huggingface.co/mosaicml/mpt-30b-chat
41
- Vicuna-13B,6.57,1041,0.558,Llama 2 Community,https://huggingface.co/lmsys/vicuna-13b-v1.5
42
- QWen-Chat-14B,6.96,1042,0.665,Qianwen LICENSE,https://huggingface.co/Qwen/Qwen-14B-Chat
43
- Zephyr-7b-alpha,6.88,1038,-,MIT,https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha
44
- CodeLlama-34B-instruct,-,1038,0.537,Llama 2 Community,https://huggingface.co/codellama/CodeLlama-34b-Instruct-hf
45
- falcon-180b-chat,-,1035,0.680,Falcon-180B TII License,https://huggingface.co/tiiuae/falcon-180B-chat
46
- Guanaco-33B,6.53,1031,0.576,Non-commercial,https://huggingface.co/timdettmers/guanaco-33b-merged
47
- Llama-2-13b-chat,6.65,1032,0.536,Llama 2 Community,https://huggingface.co/meta-llama/Llama-2-13b-chat-hf
48
- Mistral-7B-Instruct-v0.1,6.84,1023,0.554,Apache 2.0,https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1
49
- pplx-7b-online,-,1027,-,Proprietary,https://blog.perplexity.ai/blog/introducing-pplx-online-llms
50
- Llama-2-7b-chat,6.27,1015,0.458,Llama 2 Community,https://huggingface.co/meta-llama/Llama-2-7b-chat-hf
51
- Vicuna-7B,6.17,1004,0.498,Llama 2 Community,https://huggingface.co/lmsys/vicuna-7b-v1.5
52
- PaLM-Chat-Bison-001,6.40,1004,-,Proprietary,https://cloud.google.com/vertex-ai/docs/generative-ai/learn/models#foundation_models
53
- Koala-13B,5.35,966,0.447,Non-commercial,https://bair.berkeley.edu/blog/2023/04/03/koala/
54
- ChatGLM3-6B,-,960,-,Apache-2.0,https://huggingface.co/THUDM/chatglm3-6b
55
- GPT4All-13B-Snoozy,5.41,937,0.430,Non-commercial,https://huggingface.co/nomic-ai/gpt4all-13b-snoozy
56
- MPT-7B-Chat,5.42,930,0.320,CC-BY-NC-SA-4.0,https://huggingface.co/mosaicml/mpt-7b-chat
57
- ChatGLM2-6B,4.96,928,0.455,Apache-2.0,https://huggingface.co/THUDM/chatglm2-6b
58
- RWKV-4-Raven-14B,3.98,924,0.256,Apache 2.0,https://huggingface.co/BlinkDL/rwkv-4-raven
59
- Alpaca-13B,4.53,904,0.481,Non-commercial,https://crfm.stanford.edu/2023/03/13/alpaca.html
60
- OpenAssistant-Pythia-12B,4.32,896,0.270,Apache 2.0,https://huggingface.co/OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5
61
- ChatGLM-6B,4.50,882,0.361,Non-commercial,https://huggingface.co/THUDM/chatglm-6b
62
- FastChat-T5-3B,3.04,873,0.477,Apache 2.0,https://huggingface.co/lmsys/fastchat-t5-3b-v1.0
63
- StableLM-Tuned-Alpha-7B,2.75,844,0.244,CC-BY-NC-SA-4.0,https://huggingface.co/stabilityai/stablelm-tuned-alpha-7b
64
- Dolly-V2-12B,3.28,822,0.257,MIT,https://huggingface.co/databricks/dolly-v2-12b
65
- LLaMA-13B,2.61,800,0.470,Non-commercial,https://arxiv.org/abs/2302.13971
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
leaderboard_table_20231220.csv DELETED
@@ -1,66 +0,0 @@
1
- Model,MT-bench (score),Arena Elo rating,MMLU,License,Link
2
- WizardLM-30B,7.01,-,0.587,Non-commercial,https://huggingface.co/WizardLM/WizardLM-30B-V1.0
3
- Vicuna-13B-16k,6.92,-,0.545,Llama 2 Community,https://huggingface.co/lmsys/vicuna-13b-v1.5-16k
4
- WizardLM-13B-v1.1,6.76,-,0.500,Non-commercial,https://huggingface.co/WizardLM/WizardLM-13B-V1.1
5
- Tulu-30B,6.43,-,0.581,Non-commercial,https://huggingface.co/allenai/tulu-30b
6
- Guanaco-65B,6.41,-,0.621,Non-commercial,https://huggingface.co/timdettmers/guanaco-65b-merged
7
- OpenAssistant-LLaMA-30B,6.41,-,0.560,Non-commercial,https://huggingface.co/OpenAssistant/oasst-sft-6-llama-30b-xor
8
- WizardLM-13B-v1.0,6.35,-,0.523,Non-commercial,https://huggingface.co/WizardLM/WizardLM-13B-V1.0
9
- Vicuna-7B-16k,6.22,-,0.485,Llama 2 Community,https://huggingface.co/lmsys/vicuna-7b-v1.5-16k
10
- Baize-v2-13B,5.75,-,0.489,Non-commercial,https://huggingface.co/project-baize/baize-v2-13b
11
- XGen-7B-8K-Inst,5.55,-,0.421,Non-commercial,https://huggingface.co/Salesforce/xgen-7b-8k-inst
12
- Nous-Hermes-13B,5.51,-,0.493,Non-commercial,https://huggingface.co/NousResearch/Nous-Hermes-13b
13
- MPT-30B-Instruct,5.22,-,0.478,CC-BY-SA 3.0,https://huggingface.co/mosaicml/mpt-30b-instruct
14
- Falcon-40B-Instruct,5.17,-,0.547,Apache 2.0,https://huggingface.co/tiiuae/falcon-40b-instruct
15
- H2O-Oasst-OpenLLaMA-13B,4.63,-,0.428,Apache 2.0,https://huggingface.co/h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-13b
16
- GPT-4-Turbo,9.32,1243,-,Proprietary,https://openai.com/blog/new-models-and-developer-products-announced-at-devday
17
- GPT-4-0314,8.96,1192,0.864,Proprietary,https://openai.com/research/gpt-4
18
- Claude-1,7.90,1149,0.770,Proprietary,https://www.anthropic.com/index/introducing-claude
19
- GPT-4-0613,9.18,1158,-,Proprietary,https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo
20
- Claude-2.0,8.06,1131,0.785,Proprietary,https://www.anthropic.com/index/claude-2
21
- Claude-2.1,8.18,1117,-,Proprietary,https://www.anthropic.com/index/claude-2-1
22
- GPT-3.5-Turbo-0613,8.39,1117,-,Proprietary,https://platform.openai.com/docs/models/gpt-3-5
23
- Mixtral-8x7b-Instruct-v0.1,8.30,1121,0.706,Apache 2.0,https://mistral.ai/news/mixtral-of-experts/
24
- Claude-Instant-1,7.85,1110,0.734,Proprietary,https://www.anthropic.com/index/introducing-claude
25
- GPT-3.5-Turbo-0314,7.94,1105,0.700,Proprietary,https://platform.openai.com/docs/models/gpt-3-5
26
- Tulu-2-DPO-70B,7.89,1110,-,AI2 ImpACT Low-risk,https://huggingface.co/allenai/tulu-2-dpo-70b
27
- Yi-34B-Chat,-,1110,0.735,Yi License,https://huggingface.co/01-ai/Yi-34B-Chat
28
- Gemini Pro,-,1111,0.718,Proprietary,https://blog.google/technology/ai/gemini-api-developers-cloud/
29
- WizardLM-70B-v1.0,7.71,1102,0.637,Llama 2 Community,https://huggingface.co/WizardLM/WizardLM-70B-V1.0
30
- Vicuna-33B,7.12,1095,0.592,Non-commercial,https://huggingface.co/lmsys/vicuna-33b-v1.3
31
- Starling-LM-7B-alpha,8.09,1089,0.639,CC-BY-NC-4.0,https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha
32
- pplx-70b-online,-,1075,-,Proprietary,https://blog.perplexity.ai/blog/introducing-pplx-online-llms
33
- OpenChat-3.5,7.81,1077,0.643,Apache-2.0,https://huggingface.co/openchat/openchat_3.5
34
- OpenHermes-2.5-Mistral-7b,-,1074,-,Apache-2.0,https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B
35
- GPT-3.5-Turbo-1106,8.32,1074,-,Proprietary,https://platform.openai.com/docs/models/gpt-3-5
36
- Llama-2-70b-chat,6.86,1077,0.630,Llama 2 Community,https://huggingface.co/meta-llama/Llama-2-70b-chat-hf
37
- SOLAR-10.7B-Instruct-v1.0,7.58,1062,0.662,CC-BY-NC-4.0,https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0
38
- Dolphin-2.2.1-Mistral-7B,-,1059,-,Apache-2.0,https://huggingface.co/ehartford/dolphin-2.2.1-mistral-7b
39
- WizardLM-13b-v1.2,7.20,1057,0.527,Llama 2 Community,https://huggingface.co/WizardLM/WizardLM-13B-V1.2
40
- Zephyr-7b-beta,7.34,1049,0.614,MIT,https://huggingface.co/HuggingFaceH4/zephyr-7b-beta
41
- MPT-30B-chat,6.39,1042,0.504,CC-BY-NC-SA-4.0,https://huggingface.co/mosaicml/mpt-30b-chat
42
- Vicuna-13B,6.57,1041,0.558,Llama 2 Community,https://huggingface.co/lmsys/vicuna-13b-v1.5
43
- QWen-Chat-14B,6.96,1041,0.665,Qianwen LICENSE,https://huggingface.co/Qwen/Qwen-14B-Chat
44
- Zephyr-7b-alpha,6.88,1038,-,MIT,https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha
45
- CodeLlama-34B-instruct,-,1039,0.537,Llama 2 Community,https://huggingface.co/codellama/CodeLlama-34b-Instruct-hf
46
- falcon-180b-chat,-,1035,0.680,Falcon-180B TII License,https://huggingface.co/tiiuae/falcon-180B-chat
47
- Guanaco-33B,6.53,1031,0.576,Non-commercial,https://huggingface.co/timdettmers/guanaco-33b-merged
48
- Llama-2-13b-chat,6.65,1033,0.536,Llama 2 Community,https://huggingface.co/meta-llama/Llama-2-13b-chat-hf
49
- Mistral-7B-Instruct-v0.1,6.84,1023,0.554,Apache 2.0,https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1
50
- pplx-7b-online,-,1033,-,Proprietary,https://blog.perplexity.ai/blog/introducing-pplx-online-llms
51
- Llama-2-7b-chat,6.27,1016,0.458,Llama 2 Community,https://huggingface.co/meta-llama/Llama-2-7b-chat-hf
52
- Vicuna-7B,6.17,1004,0.498,Llama 2 Community,https://huggingface.co/lmsys/vicuna-7b-v1.5
53
- PaLM-Chat-Bison-001,6.40,1004,-,Proprietary,https://cloud.google.com/vertex-ai/docs/generative-ai/learn/models#foundation_models
54
- Koala-13B,5.35,965,0.447,Non-commercial,https://bair.berkeley.edu/blog/2023/04/03/koala/
55
- ChatGLM3-6B,-,959,-,Apache-2.0,https://huggingface.co/THUDM/chatglm3-6b
56
- GPT4All-13B-Snoozy,5.41,937,0.430,Non-commercial,https://huggingface.co/nomic-ai/gpt4all-13b-snoozy
57
- MPT-7B-Chat,5.42,930,0.320,CC-BY-NC-SA-4.0,https://huggingface.co/mosaicml/mpt-7b-chat
58
- ChatGLM2-6B,4.96,928,0.455,Apache-2.0,https://huggingface.co/THUDM/chatglm2-6b
59
- RWKV-4-Raven-14B,3.98,924,0.256,Apache 2.0,https://huggingface.co/BlinkDL/rwkv-4-raven
60
- Alpaca-13B,4.53,904,0.481,Non-commercial,https://crfm.stanford.edu/2023/03/13/alpaca.html
61
- OpenAssistant-Pythia-12B,4.32,896,0.270,Apache 2.0,https://huggingface.co/OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5
62
- ChatGLM-6B,4.50,882,0.361,Non-commercial,https://huggingface.co/THUDM/chatglm-6b
63
- FastChat-T5-3B,3.04,873,0.477,Apache 2.0,https://huggingface.co/lmsys/fastchat-t5-3b-v1.0
64
- StableLM-Tuned-Alpha-7B,2.75,844,0.244,CC-BY-NC-SA-4.0,https://huggingface.co/stabilityai/stablelm-tuned-alpha-7b
65
- Dolly-V2-12B,3.28,822,0.257,MIT,https://huggingface.co/databricks/dolly-v2-12b
66
- LLaMA-13B,2.61,800,0.470,Non-commercial,https://arxiv.org/abs/2302.13971
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
leaderboard_table_20240109.csv DELETED
@@ -1,69 +0,0 @@
1
- key,Model,MT-bench (score),MMLU,License,Organization,Link
2
- wizardlm-30b,WizardLM-30B,7.01,0.587,Non-commercial,Microsoft,https://huggingface.co/WizardLM/WizardLM-30B-V1.0
3
- vicuna-13b-16k,Vicuna-13B-16k,6.92,0.545,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-13b-v1.5-16k
4
- wizardlm-13b-v1.1,WizardLM-13B-v1.1,6.76,0.500,Non-commercial,Microsoft,https://huggingface.co/WizardLM/WizardLM-13B-V1.1
5
- tulu-30b,Tulu-30B,6.43,0.581,Non-commercial,AllenAI/UW,https://huggingface.co/allenai/tulu-30b
6
- guanaco-65b,Guanaco-65B,6.41,0.621,Non-commercial,UW,https://huggingface.co/timdettmers/guanaco-65b-merged
7
- openassistant-llama-30b,OpenAssistant-LLaMA-30B,6.41,0.560,Non-commercial,OpenAssistant,https://huggingface.co/OpenAssistant/oasst-sft-6-llama-30b-xor
8
- wizardlm-13b-v1.0,WizardLM-13B-v1.0,6.35,0.523,Non-commercial,Microsoft,https://huggingface.co/WizardLM/WizardLM-13B-V1.0
9
- vicuna-7b-16k,Vicuna-7B-16k,6.22,0.485,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-7b-v1.5-16k
10
- baize-v2-13b,Baize-v2-13B,5.75,0.489,Non-commercial,UCSD,https://huggingface.co/project-baize/baize-v2-13b
11
- xgen-7b-8k-inst,XGen-7B-8K-Inst,5.55,0.421,Non-commercial,Salesforce,https://huggingface.co/Salesforce/xgen-7b-8k-inst
12
- nous-hermes-13b,Nous-Hermes-13B,5.51,0.493,Non-commercial,NousResearch,https://huggingface.co/NousResearch/Nous-Hermes-13b
13
- mpt-30b-instruct,MPT-30B-Instruct,5.22,0.478,CC-BY-SA 3.0,MosaicML,https://huggingface.co/mosaicml/mpt-30b-instruct
14
- falcon-40b-instruct,Falcon-40B-Instruct,5.17,0.547,Apache 2.0,TII,https://huggingface.co/tiiuae/falcon-40b-instruct
15
- h2o-oasst-openllama-13b,H2O-Oasst-OpenLLaMA-13B,4.63,0.428,Apache 2.0,h2oai,https://huggingface.co/h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-13b
16
- gpt-4-turbo,GPT-4-Turbo,9.32,-,Proprietary,OpenAI,https://openai.com/blog/new-models-and-developer-products-announced-at-devday
17
- gpt-4-0314,GPT-4-0314,8.96,0.864,Proprietary,OpenAI,https://openai.com/research/gpt-4
18
- claude-1,Claude-1,7.90,0.770,Proprietary,Anthropic,https://www.anthropic.com/index/introducing-claude
19
- gpt-4-0613,GPT-4-0613,9.18,-,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo
20
- claude-2.0,Claude-2.0,8.06,0.785,Proprietary,Anthropic,https://www.anthropic.com/index/claude-2
21
- claude-2.1,Claude-2.1,8.18,-,Proprietary,Anthropic,https://www.anthropic.com/index/claude-2-1
22
- gpt-3.5-turbo-0613,GPT-3.5-Turbo-0613,8.39,-,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-3-5
23
- mixtral-8x7b-instruct-v0.1,Mixtral-8x7b-Instruct-v0.1,8.30,0.706,Apache 2.0,Mistral,https://mistral.ai/news/mixtral-of-experts/
24
- claude-instant-1,Claude-Instant-1,7.85,0.734,Proprietary,Anthropic,https://www.anthropic.com/index/introducing-claude
25
- gpt-3.5-turbo-0314,GPT-3.5-Turbo-0314,7.94,0.700,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-3-5
26
- tulu-2-dpo-70b,Tulu-2-DPO-70B,7.89,-,AI2 ImpACT Low-risk,AllenAI/UW,https://huggingface.co/allenai/tulu-2-dpo-70b
27
- yi-34b-chat,Yi-34B-Chat,-,0.735,Yi License,01 AI,https://huggingface.co/01-ai/Yi-34B-Chat
28
- gemini-pro,Gemini Pro,-,0.718,Proprietary,Google,https://cloud.google.com/vertex-ai/docs/generative-ai/start/quickstarts/quickstart-multimodal
29
- gemini-pro-dev-api,Gemini Pro (Dev),-,0.718,Proprietary,Google,https://ai.google.dev/docs/gemini_api_overview
30
- wizardlm-70b,WizardLM-70B-v1.0,7.71,0.637,Llama 2 Community,Microsoft,https://huggingface.co/WizardLM/WizardLM-70B-V1.0
31
- vicuna-33b,Vicuna-33B,7.12,0.592,Non-commercial,LMSYS,https://huggingface.co/lmsys/vicuna-33b-v1.3
32
- starling-lm-7b-alpha,Starling-LM-7B-alpha,8.09,0.639,CC-BY-NC-4.0,UC Berkeley,https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha
33
- pplx-70b-online,pplx-70b-online,-,-,Proprietary,Perplexity AI,https://blog.perplexity.ai/blog/introducing-pplx-online-llms
34
- openchat-3.5,OpenChat-3.5,7.81,0.643,Apache-2.0,OpenChat,https://huggingface.co/openchat/openchat_3.5
35
- openhermes-2.5-mistral-7b,OpenHermes-2.5-Mistral-7b,-,-,Apache-2.0,NousResearch,https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B
36
- gpt-3.5-turbo-1106,GPT-3.5-Turbo-1106,8.32,-,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-3-5
37
- llama-2-70b-chat,Llama-2-70b-chat,6.86,0.630,Llama 2 Community,Meta,https://huggingface.co/meta-llama/Llama-2-70b-chat-hf
38
- solar-10.7b-instruct-v1.0,SOLAR-10.7B-Instruct-v1.0,7.58,0.662,CC-BY-NC-4.0,Upstage AI,https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0
39
- dolphin-2.2.1-mistral-7b,Dolphin-2.2.1-Mistral-7B,-,-,Apache-2.0,Cognitive Computations,https://huggingface.co/ehartford/dolphin-2.2.1-mistral-7b
40
- wizardlm-13b,WizardLM-13b-v1.2,7.20,0.527,Llama 2 Community,Microsoft,https://huggingface.co/WizardLM/WizardLM-13B-V1.2
41
- zephyr-7b-beta,Zephyr-7b-beta,7.34,0.614,MIT,HuggingFace,https://huggingface.co/HuggingFaceH4/zephyr-7b-beta
42
- mpt-30b-chat,MPT-30B-chat,6.39,0.504,CC-BY-NC-SA-4.0,MosaicML,https://huggingface.co/mosaicml/mpt-30b-chat
43
- vicuna-13b,Vicuna-13B,6.57,0.558,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-13b-v1.5
44
- qwen-14b-chat,Qwen-14B-Chat,6.96,0.665,Qianwen LICENSE,Alibaba,https://huggingface.co/Qwen/Qwen-14B-Chat
45
- zephyr-7b-alpha,Zephyr-7b-alpha,6.88,-,MIT,HuggingFace,https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha
46
- codellama-34b-instruct,CodeLlama-34B-instruct,-,0.537,Llama 2 Community,Meta,https://huggingface.co/codellama/CodeLlama-34b-Instruct-hf
47
- falcon-180b-chat,falcon-180b-chat,-,0.680,Falcon-180B TII License,TII,https://huggingface.co/tiiuae/falcon-180B-chat
48
- guanaco-33b,Guanaco-33B,6.53,0.576,Non-commercial,UW,https://huggingface.co/timdettmers/guanaco-33b-merged
49
- llama-2-13b-chat,Llama-2-13b-chat,6.65,0.536,Llama 2 Community,Meta,https://huggingface.co/meta-llama/Llama-2-13b-chat-hf
50
- mistral-7b-instruct,Mistral-7B-Instruct-v0.1,6.84,0.554,Apache 2.0,Mistral,https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1
51
- pplx-7b-online,pplx-7b-online,-,-,Proprietary,Perplexity AI,https://blog.perplexity.ai/blog/introducing-pplx-online-llms
52
- llama-2-7b-chat,Llama-2-7b-chat,6.27,0.458,Llama 2 Community,Meta,https://huggingface.co/meta-llama/Llama-2-7b-chat-hf
53
- vicuna-7b,Vicuna-7B,6.17,0.498,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-7b-v1.5
54
- palm-2,PaLM-Chat-Bison-001,6.40,-,Proprietary,Google,https://cloud.google.com/vertex-ai/docs/generative-ai/learn/models#foundation_models
55
- koala-13b,Koala-13B,5.35,0.447,Non-commercial,UC Berkeley,https://bair.berkeley.edu/blog/2023/04/03/koala/
56
- chatglm3-6b,ChatGLM3-6B,-,-,Apache-2.0,Tsinghua,https://huggingface.co/THUDM/chatglm3-6b
57
- gpt4all-13b-snoozy,GPT4All-13B-Snoozy,5.41,0.430,Non-commercial,Nomic AI,https://huggingface.co/nomic-ai/gpt4all-13b-snoozy
58
- mpt-7b-chat,MPT-7B-Chat,5.42,0.320,CC-BY-NC-SA-4.0,MosaicML,https://huggingface.co/mosaicml/mpt-7b-chat
59
- chatglm2-6b,ChatGLM2-6B,4.96,0.455,Apache-2.0,Tsinghua,https://huggingface.co/THUDM/chatglm2-6b
60
- RWKV-4-Raven-14B,RWKV-4-Raven-14B,3.98,0.256,Apache 2.0,RWKV,https://huggingface.co/BlinkDL/rwkv-4-raven
61
- alpaca-13b,Alpaca-13B,4.53,0.481,Non-commercial,Stanford,https://crfm.stanford.edu/2023/03/13/alpaca.html
62
- oasst-pythia-12b,OpenAssistant-Pythia-12B,4.32,0.270,Apache 2.0,OpenAssistant,https://huggingface.co/OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5
63
- chatglm-6b,ChatGLM-6B,4.50,0.361,Non-commercial,Tsinghua,https://huggingface.co/THUDM/chatglm-6b
64
- fastchat-t5-3b,FastChat-T5-3B,3.04,0.477,Apache 2.0,LMSYS,https://huggingface.co/lmsys/fastchat-t5-3b-v1.0
65
- stablelm-tuned-alpha-7b,StableLM-Tuned-Alpha-7B,2.75,0.244,CC-BY-NC-SA-4.0,Stability AI,https://huggingface.co/stabilityai/stablelm-tuned-alpha-7b
66
- dolly-v2-12b,Dolly-V2-12B,3.28,0.257,MIT,Databricks,https://huggingface.co/databricks/dolly-v2-12b
67
- llama-13b,LLaMA-13B,2.61,0.470,Non-commercial,Meta,https://arxiv.org/abs/2302.13971
68
- mistral-medium,Mistral Medium,8.61,0.753,Proprietary,Mistral,https://mistral.ai/news/la-plateforme/
69
- llama2-70b-steerlm-chat,NV-Llama2-70B-SteerLM-Chat,7.54,0.685,Llama 2 Community,Nvidia,https://huggingface.co/nvidia/Llama2-70B-SteerLM-Chat
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
leaderboard_table_20240118.csv DELETED
@@ -1,70 +0,0 @@
1
- key,Model,MT-bench (score),MMLU,License,Organization,Link
2
- wizardlm-30b,WizardLM-30B,7.01,0.587,Non-commercial,Microsoft,https://huggingface.co/WizardLM/WizardLM-30B-V1.0
3
- vicuna-13b-16k,Vicuna-13B-16k,6.92,0.545,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-13b-v1.5-16k
4
- wizardlm-13b-v1.1,WizardLM-13B-v1.1,6.76,0.500,Non-commercial,Microsoft,https://huggingface.co/WizardLM/WizardLM-13B-V1.1
5
- tulu-30b,Tulu-30B,6.43,0.581,Non-commercial,AllenAI/UW,https://huggingface.co/allenai/tulu-30b
6
- guanaco-65b,Guanaco-65B,6.41,0.621,Non-commercial,UW,https://huggingface.co/timdettmers/guanaco-65b-merged
7
- openassistant-llama-30b,OpenAssistant-LLaMA-30B,6.41,0.560,Non-commercial,OpenAssistant,https://huggingface.co/OpenAssistant/oasst-sft-6-llama-30b-xor
8
- wizardlm-13b-v1.0,WizardLM-13B-v1.0,6.35,0.523,Non-commercial,Microsoft,https://huggingface.co/WizardLM/WizardLM-13B-V1.0
9
- vicuna-7b-16k,Vicuna-7B-16k,6.22,0.485,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-7b-v1.5-16k
10
- baize-v2-13b,Baize-v2-13B,5.75,0.489,Non-commercial,UCSD,https://huggingface.co/project-baize/baize-v2-13b
11
- xgen-7b-8k-inst,XGen-7B-8K-Inst,5.55,0.421,Non-commercial,Salesforce,https://huggingface.co/Salesforce/xgen-7b-8k-inst
12
- nous-hermes-13b,Nous-Hermes-13B,5.51,0.493,Non-commercial,NousResearch,https://huggingface.co/NousResearch/Nous-Hermes-13b
13
- mpt-30b-instruct,MPT-30B-Instruct,5.22,0.478,CC-BY-SA 3.0,MosaicML,https://huggingface.co/mosaicml/mpt-30b-instruct
14
- falcon-40b-instruct,Falcon-40B-Instruct,5.17,0.547,Apache 2.0,TII,https://huggingface.co/tiiuae/falcon-40b-instruct
15
- h2o-oasst-openllama-13b,H2O-Oasst-OpenLLaMA-13B,4.63,0.428,Apache 2.0,h2oai,https://huggingface.co/h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-13b
16
- gpt-4-turbo,GPT-4-Turbo,9.32,-,Proprietary,OpenAI,https://openai.com/blog/new-models-and-developer-products-announced-at-devday
17
- gpt-4-0314,GPT-4-0314,8.96,0.864,Proprietary,OpenAI,https://openai.com/research/gpt-4
18
- claude-1,Claude-1,7.90,0.770,Proprietary,Anthropic,https://www.anthropic.com/index/introducing-claude
19
- gpt-4-0613,GPT-4-0613,9.18,-,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo
20
- claude-2.0,Claude-2.0,8.06,0.785,Proprietary,Anthropic,https://www.anthropic.com/index/claude-2
21
- claude-2.1,Claude-2.1,8.18,-,Proprietary,Anthropic,https://www.anthropic.com/index/claude-2-1
22
- gpt-3.5-turbo-0613,GPT-3.5-Turbo-0613,8.39,-,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-3-5
23
- mixtral-8x7b-instruct-v0.1,Mixtral-8x7b-Instruct-v0.1,8.30,0.706,Apache 2.0,Mistral,https://mistral.ai/news/mixtral-of-experts/
24
- claude-instant-1,Claude-Instant-1,7.85,0.734,Proprietary,Anthropic,https://www.anthropic.com/index/introducing-claude
25
- gpt-3.5-turbo-0314,GPT-3.5-Turbo-0314,7.94,0.700,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-3-5
26
- tulu-2-dpo-70b,Tulu-2-DPO-70B,7.89,-,AI2 ImpACT Low-risk,AllenAI/UW,https://huggingface.co/allenai/tulu-2-dpo-70b
27
- yi-34b-chat,Yi-34B-Chat,-,0.735,Yi License,01 AI,https://huggingface.co/01-ai/Yi-34B-Chat
28
- gemini-pro,Gemini Pro,-,0.718,Proprietary,Google,https://cloud.google.com/vertex-ai/docs/generative-ai/start/quickstarts/quickstart-multimodal
29
- gemini-pro-dev-api,Gemini Pro (Dev),-,0.718,Proprietary,Google,https://ai.google.dev/docs/gemini_api_overview
30
- wizardlm-70b,WizardLM-70B-v1.0,7.71,0.637,Llama 2 Community,Microsoft,https://huggingface.co/WizardLM/WizardLM-70B-V1.0
31
- vicuna-33b,Vicuna-33B,7.12,0.592,Non-commercial,LMSYS,https://huggingface.co/lmsys/vicuna-33b-v1.3
32
- starling-lm-7b-alpha,Starling-LM-7B-alpha,8.09,0.639,CC-BY-NC-4.0,UC Berkeley,https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha
33
- pplx-70b-online,pplx-70b-online,-,-,Proprietary,Perplexity AI,https://blog.perplexity.ai/blog/introducing-pplx-online-llms
34
- openchat-3.5,OpenChat-3.5,7.81,0.643,Apache-2.0,OpenChat,https://huggingface.co/openchat/openchat_3.5
35
- openhermes-2.5-mistral-7b,OpenHermes-2.5-Mistral-7b,-,-,Apache-2.0,NousResearch,https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B
36
- gpt-3.5-turbo-1106,GPT-3.5-Turbo-1106,8.32,-,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-3-5
37
- llama-2-70b-chat,Llama-2-70b-chat,6.86,0.630,Llama 2 Community,Meta,https://huggingface.co/meta-llama/Llama-2-70b-chat-hf
38
- solar-10.7b-instruct-v1.0,SOLAR-10.7B-Instruct-v1.0,7.58,0.662,CC-BY-NC-4.0,Upstage AI,https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0
39
- dolphin-2.2.1-mistral-7b,Dolphin-2.2.1-Mistral-7B,-,-,Apache-2.0,Cognitive Computations,https://huggingface.co/ehartford/dolphin-2.2.1-mistral-7b
40
- wizardlm-13b,WizardLM-13b-v1.2,7.20,0.527,Llama 2 Community,Microsoft,https://huggingface.co/WizardLM/WizardLM-13B-V1.2
41
- zephyr-7b-beta,Zephyr-7b-beta,7.34,0.614,MIT,HuggingFace,https://huggingface.co/HuggingFaceH4/zephyr-7b-beta
42
- mpt-30b-chat,MPT-30B-chat,6.39,0.504,CC-BY-NC-SA-4.0,MosaicML,https://huggingface.co/mosaicml/mpt-30b-chat
43
- vicuna-13b,Vicuna-13B,6.57,0.558,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-13b-v1.5
44
- qwen-14b-chat,Qwen-14B-Chat,6.96,0.665,Qianwen LICENSE,Alibaba,https://huggingface.co/Qwen/Qwen-14B-Chat
45
- zephyr-7b-alpha,Zephyr-7b-alpha,6.88,-,MIT,HuggingFace,https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha
46
- codellama-34b-instruct,CodeLlama-34B-instruct,-,0.537,Llama 2 Community,Meta,https://huggingface.co/codellama/CodeLlama-34b-Instruct-hf
47
- falcon-180b-chat,falcon-180b-chat,-,0.680,Falcon-180B TII License,TII,https://huggingface.co/tiiuae/falcon-180B-chat
48
- guanaco-33b,Guanaco-33B,6.53,0.576,Non-commercial,UW,https://huggingface.co/timdettmers/guanaco-33b-merged
49
- llama-2-13b-chat,Llama-2-13b-chat,6.65,0.536,Llama 2 Community,Meta,https://huggingface.co/meta-llama/Llama-2-13b-chat-hf
50
- mistral-7b-instruct,Mistral-7B-Instruct-v0.1,6.84,0.554,Apache 2.0,Mistral,https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1
51
- pplx-7b-online,pplx-7b-online,-,-,Proprietary,Perplexity AI,https://blog.perplexity.ai/blog/introducing-pplx-online-llms
52
- llama-2-7b-chat,Llama-2-7b-chat,6.27,0.458,Llama 2 Community,Meta,https://huggingface.co/meta-llama/Llama-2-7b-chat-hf
53
- vicuna-7b,Vicuna-7B,6.17,0.498,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-7b-v1.5
54
- palm-2,PaLM-Chat-Bison-001,6.40,-,Proprietary,Google,https://cloud.google.com/vertex-ai/docs/generative-ai/learn/models#foundation_models
55
- koala-13b,Koala-13B,5.35,0.447,Non-commercial,UC Berkeley,https://bair.berkeley.edu/blog/2023/04/03/koala/
56
- chatglm3-6b,ChatGLM3-6B,-,-,Apache-2.0,Tsinghua,https://huggingface.co/THUDM/chatglm3-6b
57
- gpt4all-13b-snoozy,GPT4All-13B-Snoozy,5.41,0.430,Non-commercial,Nomic AI,https://huggingface.co/nomic-ai/gpt4all-13b-snoozy
58
- mpt-7b-chat,MPT-7B-Chat,5.42,0.320,CC-BY-NC-SA-4.0,MosaicML,https://huggingface.co/mosaicml/mpt-7b-chat
59
- chatglm2-6b,ChatGLM2-6B,4.96,0.455,Apache-2.0,Tsinghua,https://huggingface.co/THUDM/chatglm2-6b
60
- RWKV-4-Raven-14B,RWKV-4-Raven-14B,3.98,0.256,Apache 2.0,RWKV,https://huggingface.co/BlinkDL/rwkv-4-raven
61
- alpaca-13b,Alpaca-13B,4.53,0.481,Non-commercial,Stanford,https://crfm.stanford.edu/2023/03/13/alpaca.html
62
- oasst-pythia-12b,OpenAssistant-Pythia-12B,4.32,0.270,Apache 2.0,OpenAssistant,https://huggingface.co/OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5
63
- chatglm-6b,ChatGLM-6B,4.50,0.361,Non-commercial,Tsinghua,https://huggingface.co/THUDM/chatglm-6b
64
- fastchat-t5-3b,FastChat-T5-3B,3.04,0.477,Apache 2.0,LMSYS,https://huggingface.co/lmsys/fastchat-t5-3b-v1.0
65
- stablelm-tuned-alpha-7b,StableLM-Tuned-Alpha-7B,2.75,0.244,CC-BY-NC-SA-4.0,Stability AI,https://huggingface.co/stabilityai/stablelm-tuned-alpha-7b
66
- dolly-v2-12b,Dolly-V2-12B,3.28,0.257,MIT,Databricks,https://huggingface.co/databricks/dolly-v2-12b
67
- llama-13b,LLaMA-13B,2.61,0.470,Non-commercial,Meta,https://arxiv.org/abs/2302.13971
68
- mistral-medium,Mistral Medium,8.61,0.753,Proprietary,Mistral,https://mistral.ai/news/la-plateforme/
69
- llama2-70b-steerlm-chat,Llama2-70B-SteerLM-Chat,7.54,-,Llama 2 Community,Nvidia,https://huggingface.co/nvidia/Llama2-70B-SteerLM-Chat
70
- stripedhyena-nous-7b,StripedHyena-Nous-7B,-,-,Apache 2.0,Together AI,https://huggingface.co/togethercomputer/StripedHyena-Nous-7B
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
leaderboard_table_20240125.csv DELETED
@@ -1,72 +0,0 @@
1
- key,Model,MT-bench (score),MMLU,Knowledge cutoff date,License,Organization,Link
2
- wizardlm-30b,WizardLM-30B,7.01,0.587,2023/6,Non-commercial,Microsoft,https://huggingface.co/WizardLM/WizardLM-30B-V1.0
3
- vicuna-13b-16k,Vicuna-13B-16k,6.92,0.545,2023/7,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-13b-v1.5-16k
4
- wizardlm-13b-v1.1,WizardLM-13B-v1.1,6.76,0.500,2023/7,Non-commercial,Microsoft,https://huggingface.co/WizardLM/WizardLM-13B-V1.1
5
- tulu-30b,Tulu-30B,6.43,0.581,2023/6,Non-commercial,AllenAI/UW,https://huggingface.co/allenai/tulu-30b
6
- guanaco-65b,Guanaco-65B,6.41,0.621,2023/5,Non-commercial,UW,https://huggingface.co/timdettmers/guanaco-65b-merged
7
- openassistant-llama-30b,OpenAssistant-LLaMA-30B,6.41,0.560,2023/4,Non-commercial,OpenAssistant,https://huggingface.co/OpenAssistant/oasst-sft-6-llama-30b-xor
8
- wizardlm-13b-v1.0,WizardLM-13B-v1.0,6.35,0.523,2023/5,Non-commercial,Microsoft,https://huggingface.co/WizardLM/WizardLM-13B-V1.0
9
- vicuna-7b-16k,Vicuna-7B-16k,6.22,0.485,2023/7,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-7b-v1.5-16k
10
- baize-v2-13b,Baize-v2-13B,5.75,0.489,2023/4,Non-commercial,UCSD,https://huggingface.co/project-baize/baize-v2-13b
11
- xgen-7b-8k-inst,XGen-7B-8K-Inst,5.55,0.421,2023/7,Non-commercial,Salesforce,https://huggingface.co/Salesforce/xgen-7b-8k-inst
12
- nous-hermes-13b,Nous-Hermes-13B,5.51,0.493,2023/6,Non-commercial,NousResearch,https://huggingface.co/NousResearch/Nous-Hermes-13b
13
- mpt-30b-instruct,MPT-30B-Instruct,5.22,0.478,2023/6,CC-BY-SA 3.0,MosaicML,https://huggingface.co/mosaicml/mpt-30b-instruct
14
- falcon-40b-instruct,Falcon-40B-Instruct,5.17,0.547,2023/5,Apache 2.0,TII,https://huggingface.co/tiiuae/falcon-40b-instruct
15
- h2o-oasst-openllama-13b,H2O-Oasst-OpenLLaMA-13B,4.63,0.428,2023/6,Apache 2.0,h2oai,https://huggingface.co/h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-13b
16
- gpt-4-turbo,GPT-4-Turbo,9.32,-,2023/4,Proprietary,OpenAI,https://openai.com/blog/new-models-and-developer-products-announced-at-devday
17
- gpt-4-0314,GPT-4-0314,8.96,0.864,2021/9,Proprietary,OpenAI,https://openai.com/research/gpt-4
18
- claude-1,Claude-1,7.90,0.770,-,Proprietary,Anthropic,https://www.anthropic.com/index/introducing-claude
19
- gpt-4-0613,GPT-4-0613,9.18,-,2021/9,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo
20
- claude-2.0,Claude-2.0,8.06,0.785,-,Proprietary,Anthropic,https://www.anthropic.com/index/claude-2
21
- claude-2.1,Claude-2.1,8.18,-,-,Proprietary,Anthropic,https://www.anthropic.com/index/claude-2-1
22
- gpt-3.5-turbo-0613,GPT-3.5-Turbo-0613,8.39,-,2021/9,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-3-5
23
- mixtral-8x7b-instruct-v0.1,Mixtral-8x7b-Instruct-v0.1,8.30,0.706,2023/12,Apache 2.0,Mistral,https://mistral.ai/news/mixtral-of-experts/
24
- claude-instant-1,Claude-Instant-1,7.85,0.734,-,Proprietary,Anthropic,https://www.anthropic.com/index/introducing-claude
25
- gpt-3.5-turbo-0314,GPT-3.5-Turbo-0314,7.94,0.700,2021/9,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-3-5
26
- tulu-2-dpo-70b,Tulu-2-DPO-70B,7.89,-,2023/11,AI2 ImpACT Low-risk,AllenAI/UW,https://huggingface.co/allenai/tulu-2-dpo-70b
27
- yi-34b-chat,Yi-34B-Chat,-,0.735,2023/6,Yi License,01 AI,https://huggingface.co/01-ai/Yi-34B-Chat
28
- gemini-pro,Gemini Pro,-,0.718,2023/4,Proprietary,Google,https://blog.google/technology/ai/gemini-api-developers-cloud/
29
- gemini-pro-dev-api,Gemini Pro (Dev API),-,0.718,2023/4,Proprietary,Google,https://ai.google.dev/docs/gemini_api_overview
30
- bard-jan-24-gemini-pro,Bard (Gemini Pro),-,-,Online,Proprietary,Google,https://bard.google.com/
31
- wizardlm-70b,WizardLM-70B-v1.0,7.71,0.637,2023/8,Llama 2 Community,Microsoft,https://huggingface.co/WizardLM/WizardLM-70B-V1.0
32
- vicuna-33b,Vicuna-33B,7.12,0.592,2023/8,Non-commercial,LMSYS,https://huggingface.co/lmsys/vicuna-33b-v1.3
33
- starling-lm-7b-alpha,Starling-LM-7B-alpha,8.09,0.639,2023/11,CC-BY-NC-4.0,UC Berkeley,https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha
34
- pplx-70b-online,pplx-70b-online,-,-,Online,Proprietary,Perplexity AI,https://blog.perplexity.ai/blog/introducing-pplx-online-llms
35
- openchat-3.5,OpenChat-3.5,7.81,0.643,2023/11,Apache-2.0,OpenChat,https://huggingface.co/openchat/openchat_3.5
36
- openhermes-2.5-mistral-7b,OpenHermes-2.5-Mistral-7b,-,-,2023/11,Apache-2.0,NousResearch,https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B
37
- gpt-3.5-turbo-1106,GPT-3.5-Turbo-1106,8.32,-,2021/9,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-3-5
38
- llama-2-70b-chat,Llama-2-70b-chat,6.86,0.630,2023/7,Llama 2 Community,Meta,https://huggingface.co/meta-llama/Llama-2-70b-chat-hf
39
- solar-10.7b-instruct-v1.0,SOLAR-10.7B-Instruct-v1.0,7.58,0.662,2023/11,CC-BY-NC-4.0,Upstage AI,https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0
40
- dolphin-2.2.1-mistral-7b,Dolphin-2.2.1-Mistral-7B,-,-,2023/10,Apache-2.0,Cognitive Computations,https://huggingface.co/ehartford/dolphin-2.2.1-mistral-7b
41
- wizardlm-13b,WizardLM-13b-v1.2,7.20,0.527,2023/7,Llama 2 Community,Microsoft,https://huggingface.co/WizardLM/WizardLM-13B-V1.2
42
- zephyr-7b-beta,Zephyr-7b-beta,7.34,0.614,2023/10,MIT,HuggingFace,https://huggingface.co/HuggingFaceH4/zephyr-7b-beta
43
- mpt-30b-chat,MPT-30B-chat,6.39,0.504,2023/6,CC-BY-NC-SA-4.0,MosaicML,https://huggingface.co/mosaicml/mpt-30b-chat
44
- vicuna-13b,Vicuna-13B,6.57,0.558,2023/7,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-13b-v1.5
45
- qwen-14b-chat,Qwen-14B-Chat,6.96,0.665,2023/8,Qianwen LICENSE,Alibaba,https://huggingface.co/Qwen/Qwen-14B-Chat
46
- zephyr-7b-alpha,Zephyr-7b-alpha,6.88,-,2023/10,MIT,HuggingFace,https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha
47
- codellama-34b-instruct,CodeLlama-34B-instruct,-,0.537,2023/7,Llama 2 Community,Meta,https://huggingface.co/codellama/CodeLlama-34b-Instruct-hf
48
- falcon-180b-chat,falcon-180b-chat,-,0.680,2023/9,Falcon-180B TII License,TII,https://huggingface.co/tiiuae/falcon-180B-chat
49
- guanaco-33b,Guanaco-33B,6.53,0.576,2023/5,Non-commercial,UW,https://huggingface.co/timdettmers/guanaco-33b-merged
50
- llama-2-13b-chat,Llama-2-13b-chat,6.65,0.536,2023/7,Llama 2 Community,Meta,https://huggingface.co/meta-llama/Llama-2-13b-chat-hf
51
- mistral-7b-instruct,Mistral-7B-Instruct-v0.1,6.84,0.554,2023/9,Apache 2.0,Mistral,https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1
52
- pplx-7b-online,pplx-7b-online,-,-,Online,Proprietary,Perplexity AI,https://blog.perplexity.ai/blog/introducing-pplx-online-llms
53
- llama-2-7b-chat,Llama-2-7b-chat,6.27,0.458,2023/7,Llama 2 Community,Meta,https://huggingface.co/meta-llama/Llama-2-7b-chat-hf
54
- vicuna-7b,Vicuna-7B,6.17,0.498,2023/7,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-7b-v1.5
55
- palm-2,PaLM-Chat-Bison-001,6.40,-,2021/6,Proprietary,Google,https://cloud.google.com/vertex-ai/docs/generative-ai/learn/models#foundation_models
56
- koala-13b,Koala-13B,5.35,0.447,2023/4,Non-commercial,UC Berkeley,https://bair.berkeley.edu/blog/2023/04/03/koala/
57
- chatglm3-6b,ChatGLM3-6B,-,-,2023/10,Apache-2.0,Tsinghua,https://huggingface.co/THUDM/chatglm3-6b
58
- gpt4all-13b-snoozy,GPT4All-13B-Snoozy,5.41,0.430,2023/3,Non-commercial,Nomic AI,https://huggingface.co/nomic-ai/gpt4all-13b-snoozy
59
- mpt-7b-chat,MPT-7B-Chat,5.42,0.320,2023/5,CC-BY-NC-SA-4.0,MosaicML,https://huggingface.co/mosaicml/mpt-7b-chat
60
- chatglm2-6b,ChatGLM2-6B,4.96,0.455,2023/6,Apache-2.0,Tsinghua,https://huggingface.co/THUDM/chatglm2-6b
61
- RWKV-4-Raven-14B,RWKV-4-Raven-14B,3.98,0.256,2023/4,Apache 2.0,RWKV,https://huggingface.co/BlinkDL/rwkv-4-raven
62
- alpaca-13b,Alpaca-13B,4.53,0.481,2023/3,Non-commercial,Stanford,https://crfm.stanford.edu/2023/03/13/alpaca.html
63
- oasst-pythia-12b,OpenAssistant-Pythia-12B,4.32,0.270,2023/4,Apache 2.0,OpenAssistant,https://huggingface.co/OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5
64
- chatglm-6b,ChatGLM-6B,4.50,0.361,2023/3,Non-commercial,Tsinghua,https://huggingface.co/THUDM/chatglm-6b
65
- fastchat-t5-3b,FastChat-T5-3B,3.04,0.477,2023/4,Apache 2.0,LMSYS,https://huggingface.co/lmsys/fastchat-t5-3b-v1.0
66
- stablelm-tuned-alpha-7b,StableLM-Tuned-Alpha-7B,2.75,0.244,2023/4,CC-BY-NC-SA-4.0,Stability AI,https://huggingface.co/stabilityai/stablelm-tuned-alpha-7b
67
- dolly-v2-12b,Dolly-V2-12B,3.28,0.257,2023/4,MIT,Databricks,https://huggingface.co/databricks/dolly-v2-12b
68
- llama-13b,LLaMA-13B,2.61,0.470,2023/2,Non-commercial,Meta,https://arxiv.org/abs/2302.13971
69
- mistral-medium,Mistral Medium,8.61,0.753,-,Proprietary,Mistral,https://mistral.ai/news/la-plateforme/
70
- llama2-70b-steerlm-chat,NV-Llama2-70B-SteerLM-Chat,7.54,0.685,2023/11,Llama 2 Community,Nvidia,https://huggingface.co/nvidia/Llama2-70B-SteerLM-Chat
71
- stripedhyena-nous-7b,StripedHyena-Nous-7B,-,-,2023/12,Apache 2.0,Together AI,https://huggingface.co/togethercomputer/StripedHyena-Nous-7B
72
- deepseek-llm-67b-chat,DeepSeek-LLM-67B-Chat,-,0.713,2023/11,DeepSeek License,DeepSeek AI,https://huggingface.co/deepseek-ai/deepseek-llm-67b-chat
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
leaderboard_table_20240202.csv DELETED
@@ -1,73 +0,0 @@
1
- key,Model,MT-bench (score),MMLU,Knowledge cutoff date,License,Organization,Link
2
- wizardlm-30b,WizardLM-30B,7.01,0.587,2023/6,Non-commercial,Microsoft,https://huggingface.co/WizardLM/WizardLM-30B-V1.0
3
- vicuna-13b-16k,Vicuna-13B-16k,6.92,0.545,2023/7,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-13b-v1.5-16k
4
- wizardlm-13b-v1.1,WizardLM-13B-v1.1,6.76,0.500,2023/7,Non-commercial,Microsoft,https://huggingface.co/WizardLM/WizardLM-13B-V1.1
5
- tulu-30b,Tulu-30B,6.43,0.581,2023/6,Non-commercial,AllenAI/UW,https://huggingface.co/allenai/tulu-30b
6
- guanaco-65b,Guanaco-65B,6.41,0.621,2023/5,Non-commercial,UW,https://huggingface.co/timdettmers/guanaco-65b-merged
7
- openassistant-llama-30b,OpenAssistant-LLaMA-30B,6.41,0.560,2023/4,Non-commercial,OpenAssistant,https://huggingface.co/OpenAssistant/oasst-sft-6-llama-30b-xor
8
- wizardlm-13b-v1.0,WizardLM-13B-v1.0,6.35,0.523,2023/5,Non-commercial,Microsoft,https://huggingface.co/WizardLM/WizardLM-13B-V1.0
9
- vicuna-7b-16k,Vicuna-7B-16k,6.22,0.485,2023/7,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-7b-v1.5-16k
10
- baize-v2-13b,Baize-v2-13B,5.75,0.489,2023/4,Non-commercial,UCSD,https://huggingface.co/project-baize/baize-v2-13b
11
- xgen-7b-8k-inst,XGen-7B-8K-Inst,5.55,0.421,2023/7,Non-commercial,Salesforce,https://huggingface.co/Salesforce/xgen-7b-8k-inst
12
- nous-hermes-13b,Nous-Hermes-13B,5.51,0.493,2023/6,Non-commercial,NousResearch,https://huggingface.co/NousResearch/Nous-Hermes-13b
13
- mpt-30b-instruct,MPT-30B-Instruct,5.22,0.478,2023/6,CC-BY-SA 3.0,MosaicML,https://huggingface.co/mosaicml/mpt-30b-instruct
14
- falcon-40b-instruct,Falcon-40B-Instruct,5.17,0.547,2023/5,Apache 2.0,TII,https://huggingface.co/tiiuae/falcon-40b-instruct
15
- h2o-oasst-openllama-13b,H2O-Oasst-OpenLLaMA-13B,4.63,0.428,2023/6,Apache 2.0,h2oai,https://huggingface.co/h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-13b
16
- gpt-4-1106-preview,GPT-4-1106-preview,9.32,-,2023/4,Proprietary,OpenAI,https://openai.com/blog/new-models-and-developer-products-announced-at-devday
17
- gpt-4-0314,GPT-4-0314,8.96,0.864,2021/9,Proprietary,OpenAI,https://openai.com/research/gpt-4
18
- claude-1,Claude-1,7.90,0.770,-,Proprietary,Anthropic,https://www.anthropic.com/index/introducing-claude
19
- gpt-4-0613,GPT-4-0613,9.18,-,2021/9,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo
20
- claude-2.0,Claude-2.0,8.06,0.785,-,Proprietary,Anthropic,https://www.anthropic.com/index/claude-2
21
- claude-2.1,Claude-2.1,8.18,-,-,Proprietary,Anthropic,https://www.anthropic.com/index/claude-2-1
22
- gpt-3.5-turbo-0613,GPT-3.5-Turbo-0613,8.39,-,2021/9,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-3-5
23
- mixtral-8x7b-instruct-v0.1,Mixtral-8x7b-Instruct-v0.1,8.30,0.706,2023/12,Apache 2.0,Mistral,https://mistral.ai/news/mixtral-of-experts/
24
- claude-instant-1,Claude-Instant-1,7.85,0.734,-,Proprietary,Anthropic,https://www.anthropic.com/index/introducing-claude
25
- gpt-3.5-turbo-0314,GPT-3.5-Turbo-0314,7.94,0.700,2021/9,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-3-5
26
- tulu-2-dpo-70b,Tulu-2-DPO-70B,7.89,-,2023/11,AI2 ImpACT Low-risk,AllenAI/UW,https://huggingface.co/allenai/tulu-2-dpo-70b
27
- yi-34b-chat,Yi-34B-Chat,-,0.735,2023/6,Yi License,01 AI,https://huggingface.co/01-ai/Yi-34B-Chat
28
- gemini-pro,Gemini Pro,-,0.718,2023/4,Proprietary,Google,https://blog.google/technology/ai/gemini-api-developers-cloud/
29
- gemini-pro-dev-api,Gemini Pro (Dev API),-,0.718,2023/4,Proprietary,Google,https://ai.google.dev/docs/gemini_api_overview
30
- bard-jan-24-gemini-pro,Bard (Gemini Pro),-,-,Online,Proprietary,Google,https://bard.google.com/
31
- wizardlm-70b,WizardLM-70B-v1.0,7.71,0.637,2023/8,Llama 2 Community,Microsoft,https://huggingface.co/WizardLM/WizardLM-70B-V1.0
32
- vicuna-33b,Vicuna-33B,7.12,0.592,2023/8,Non-commercial,LMSYS,https://huggingface.co/lmsys/vicuna-33b-v1.3
33
- starling-lm-7b-alpha,Starling-LM-7B-alpha,8.09,0.639,2023/11,CC-BY-NC-4.0,UC Berkeley,https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha
34
- pplx-70b-online,pplx-70b-online,-,-,Online,Proprietary,Perplexity AI,https://blog.perplexity.ai/blog/introducing-pplx-online-llms
35
- openchat-3.5,OpenChat-3.5,7.81,0.643,2023/11,Apache-2.0,OpenChat,https://huggingface.co/openchat/openchat_3.5
36
- openhermes-2.5-mistral-7b,OpenHermes-2.5-Mistral-7b,-,-,2023/11,Apache-2.0,NousResearch,https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B
37
- gpt-3.5-turbo-1106,GPT-3.5-Turbo-1106,8.32,-,2021/9,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-3-5
38
- llama-2-70b-chat,Llama-2-70b-chat,6.86,0.630,2023/7,Llama 2 Community,Meta,https://huggingface.co/meta-llama/Llama-2-70b-chat-hf
39
- solar-10.7b-instruct-v1.0,SOLAR-10.7B-Instruct-v1.0,7.58,0.662,2023/11,CC-BY-NC-4.0,Upstage AI,https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0
40
- dolphin-2.2.1-mistral-7b,Dolphin-2.2.1-Mistral-7B,-,-,2023/10,Apache-2.0,Cognitive Computations,https://huggingface.co/ehartford/dolphin-2.2.1-mistral-7b
41
- wizardlm-13b,WizardLM-13b-v1.2,7.20,0.527,2023/7,Llama 2 Community,Microsoft,https://huggingface.co/WizardLM/WizardLM-13B-V1.2
42
- zephyr-7b-beta,Zephyr-7b-beta,7.34,0.614,2023/10,MIT,HuggingFace,https://huggingface.co/HuggingFaceH4/zephyr-7b-beta
43
- mpt-30b-chat,MPT-30B-chat,6.39,0.504,2023/6,CC-BY-NC-SA-4.0,MosaicML,https://huggingface.co/mosaicml/mpt-30b-chat
44
- vicuna-13b,Vicuna-13B,6.57,0.558,2023/7,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-13b-v1.5
45
- qwen-14b-chat,Qwen-14B-Chat,6.96,0.665,2023/8,Qianwen LICENSE,Alibaba,https://huggingface.co/Qwen/Qwen-14B-Chat
46
- zephyr-7b-alpha,Zephyr-7b-alpha,6.88,-,2023/10,MIT,HuggingFace,https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha
47
- codellama-34b-instruct,CodeLlama-34B-instruct,-,0.537,2023/7,Llama 2 Community,Meta,https://huggingface.co/codellama/CodeLlama-34b-Instruct-hf
48
- falcon-180b-chat,falcon-180b-chat,-,0.680,2023/9,Falcon-180B TII License,TII,https://huggingface.co/tiiuae/falcon-180B-chat
49
- guanaco-33b,Guanaco-33B,6.53,0.576,2023/5,Non-commercial,UW,https://huggingface.co/timdettmers/guanaco-33b-merged
50
- llama-2-13b-chat,Llama-2-13b-chat,6.65,0.536,2023/7,Llama 2 Community,Meta,https://huggingface.co/meta-llama/Llama-2-13b-chat-hf
51
- mistral-7b-instruct,Mistral-7B-Instruct-v0.1,6.84,0.554,2023/9,Apache 2.0,Mistral,https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1
52
- pplx-7b-online,pplx-7b-online,-,-,Online,Proprietary,Perplexity AI,https://blog.perplexity.ai/blog/introducing-pplx-online-llms
53
- llama-2-7b-chat,Llama-2-7b-chat,6.27,0.458,2023/7,Llama 2 Community,Meta,https://huggingface.co/meta-llama/Llama-2-7b-chat-hf
54
- vicuna-7b,Vicuna-7B,6.17,0.498,2023/7,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-7b-v1.5
55
- palm-2,PaLM-Chat-Bison-001,6.40,-,2021/6,Proprietary,Google,https://cloud.google.com/vertex-ai/docs/generative-ai/learn/models#foundation_models
56
- koala-13b,Koala-13B,5.35,0.447,2023/4,Non-commercial,UC Berkeley,https://bair.berkeley.edu/blog/2023/04/03/koala/
57
- chatglm3-6b,ChatGLM3-6B,-,-,2023/10,Apache-2.0,Tsinghua,https://huggingface.co/THUDM/chatglm3-6b
58
- gpt4all-13b-snoozy,GPT4All-13B-Snoozy,5.41,0.430,2023/3,Non-commercial,Nomic AI,https://huggingface.co/nomic-ai/gpt4all-13b-snoozy
59
- mpt-7b-chat,MPT-7B-Chat,5.42,0.320,2023/5,CC-BY-NC-SA-4.0,MosaicML,https://huggingface.co/mosaicml/mpt-7b-chat
60
- chatglm2-6b,ChatGLM2-6B,4.96,0.455,2023/6,Apache-2.0,Tsinghua,https://huggingface.co/THUDM/chatglm2-6b
61
- RWKV-4-Raven-14B,RWKV-4-Raven-14B,3.98,0.256,2023/4,Apache 2.0,RWKV,https://huggingface.co/BlinkDL/rwkv-4-raven
62
- alpaca-13b,Alpaca-13B,4.53,0.481,2023/3,Non-commercial,Stanford,https://crfm.stanford.edu/2023/03/13/alpaca.html
63
- oasst-pythia-12b,OpenAssistant-Pythia-12B,4.32,0.270,2023/4,Apache 2.0,OpenAssistant,https://huggingface.co/OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5
64
- chatglm-6b,ChatGLM-6B,4.50,0.361,2023/3,Non-commercial,Tsinghua,https://huggingface.co/THUDM/chatglm-6b
65
- fastchat-t5-3b,FastChat-T5-3B,3.04,0.477,2023/4,Apache 2.0,LMSYS,https://huggingface.co/lmsys/fastchat-t5-3b-v1.0
66
- stablelm-tuned-alpha-7b,StableLM-Tuned-Alpha-7B,2.75,0.244,2023/4,CC-BY-NC-SA-4.0,Stability AI,https://huggingface.co/stabilityai/stablelm-tuned-alpha-7b
67
- dolly-v2-12b,Dolly-V2-12B,3.28,0.257,2023/4,MIT,Databricks,https://huggingface.co/databricks/dolly-v2-12b
68
- llama-13b,LLaMA-13B,2.61,0.470,2023/2,Non-commercial,Meta,https://arxiv.org/abs/2302.13971
69
- mistral-medium,Mistral Medium,8.61,0.753,-,Proprietary,Mistral,https://mistral.ai/news/la-plateforme/
70
- llama2-70b-steerlm-chat,NV-Llama2-70B-SteerLM-Chat,7.54,0.685,2023/11,Llama 2 Community,Nvidia,https://huggingface.co/nvidia/Llama2-70B-SteerLM-Chat
71
- stripedhyena-nous-7b,StripedHyena-Nous-7B,-,-,2023/12,Apache 2.0,Together AI,https://huggingface.co/togethercomputer/StripedHyena-Nous-7B
72
- deepseek-llm-67b-chat,DeepSeek-LLM-67B-Chat,-,0.713,2023/11,DeepSeek License,DeepSeek AI,https://huggingface.co/deepseek-ai/deepseek-llm-67b-chat
73
- gpt-4-0125-preview,GPT-4-0125-preview,-,-,2023/4,Proprietary,OpenAI,https://openai.com/blog/new-models-and-developer-products-announced-at-devday
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
leaderboard_table_20240215.csv DELETED
@@ -1,79 +0,0 @@
1
- key,Model,MT-bench (score),MMLU,Knowledge cutoff date,License,Organization,Link
2
- wizardlm-30b,WizardLM-30B,7.01,0.587,2023/6,Non-commercial,Microsoft,https://huggingface.co/WizardLM/WizardLM-30B-V1.0
3
- vicuna-13b-16k,Vicuna-13B-16k,6.92,0.545,2023/7,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-13b-v1.5-16k
4
- wizardlm-13b-v1.1,WizardLM-13B-v1.1,6.76,0.500,2023/7,Non-commercial,Microsoft,https://huggingface.co/WizardLM/WizardLM-13B-V1.1
5
- tulu-30b,Tulu-30B,6.43,0.581,2023/6,Non-commercial,AllenAI/UW,https://huggingface.co/allenai/tulu-30b
6
- guanaco-65b,Guanaco-65B,6.41,0.621,2023/5,Non-commercial,UW,https://huggingface.co/timdettmers/guanaco-65b-merged
7
- openassistant-llama-30b,OpenAssistant-LLaMA-30B,6.41,0.560,2023/4,Non-commercial,OpenAssistant,https://huggingface.co/OpenAssistant/oasst-sft-6-llama-30b-xor
8
- wizardlm-13b-v1.0,WizardLM-13B-v1.0,6.35,0.523,2023/5,Non-commercial,Microsoft,https://huggingface.co/WizardLM/WizardLM-13B-V1.0
9
- vicuna-7b-16k,Vicuna-7B-16k,6.22,0.485,2023/7,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-7b-v1.5-16k
10
- baize-v2-13b,Baize-v2-13B,5.75,0.489,2023/4,Non-commercial,UCSD,https://huggingface.co/project-baize/baize-v2-13b
11
- xgen-7b-8k-inst,XGen-7B-8K-Inst,5.55,0.421,2023/7,Non-commercial,Salesforce,https://huggingface.co/Salesforce/xgen-7b-8k-inst
12
- nous-hermes-13b,Nous-Hermes-13B,5.51,0.493,2023/6,Non-commercial,NousResearch,https://huggingface.co/NousResearch/Nous-Hermes-13b
13
- mpt-30b-instruct,MPT-30B-Instruct,5.22,0.478,2023/6,CC-BY-SA 3.0,MosaicML,https://huggingface.co/mosaicml/mpt-30b-instruct
14
- falcon-40b-instruct,Falcon-40B-Instruct,5.17,0.547,2023/5,Apache 2.0,TII,https://huggingface.co/tiiuae/falcon-40b-instruct
15
- h2o-oasst-openllama-13b,H2O-Oasst-OpenLLaMA-13B,4.63,0.428,2023/6,Apache 2.0,h2oai,https://huggingface.co/h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-13b
16
- gpt-4-1106-preview,GPT-4-1106-preview,9.32,-,2023/4,Proprietary,OpenAI,https://openai.com/blog/new-models-and-developer-products-announced-at-devday
17
- gpt-4-0314,GPT-4-0314,8.96,0.864,2021/9,Proprietary,OpenAI,https://openai.com/research/gpt-4
18
- claude-1,Claude-1,7.90,0.770,-,Proprietary,Anthropic,https://www.anthropic.com/index/introducing-claude
19
- gpt-4-0613,GPT-4-0613,9.18,-,2021/9,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo
20
- claude-2.0,Claude-2.0,8.06,0.785,-,Proprietary,Anthropic,https://www.anthropic.com/index/claude-2
21
- claude-2.1,Claude-2.1,8.18,-,-,Proprietary,Anthropic,https://www.anthropic.com/index/claude-2-1
22
- gpt-3.5-turbo-0613,GPT-3.5-Turbo-0613,8.39,-,2021/9,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-3-5
23
- mixtral-8x7b-instruct-v0.1,Mixtral-8x7b-Instruct-v0.1,8.30,0.706,2023/12,Apache 2.0,Mistral,https://mistral.ai/news/mixtral-of-experts/
24
- claude-instant-1,Claude-Instant-1,7.85,0.734,-,Proprietary,Anthropic,https://www.anthropic.com/index/introducing-claude
25
- gpt-3.5-turbo-0314,GPT-3.5-Turbo-0314,7.94,0.700,2021/9,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-3-5
26
- tulu-2-dpo-70b,Tulu-2-DPO-70B,7.89,-,2023/11,AI2 ImpACT Low-risk,AllenAI/UW,https://huggingface.co/allenai/tulu-2-dpo-70b
27
- yi-34b-chat,Yi-34B-Chat,-,0.735,2023/6,Yi License,01 AI,https://huggingface.co/01-ai/Yi-34B-Chat
28
- gemini-pro,Gemini Pro,-,0.718,2023/4,Proprietary,Google,https://blog.google/technology/ai/gemini-api-developers-cloud/
29
- gemini-pro-dev-api,Gemini Pro (Dev API),-,0.718,2023/4,Proprietary,Google,https://ai.google.dev/docs/gemini_api_overview
30
- bard-jan-24-gemini-pro,Bard (Gemini Pro),-,-,Online,Proprietary,Google,https://bard.google.com/
31
- wizardlm-70b,WizardLM-70B-v1.0,7.71,0.637,2023/8,Llama 2 Community,Microsoft,https://huggingface.co/WizardLM/WizardLM-70B-V1.0
32
- vicuna-33b,Vicuna-33B,7.12,0.592,2023/8,Non-commercial,LMSYS,https://huggingface.co/lmsys/vicuna-33b-v1.3
33
- starling-lm-7b-alpha,Starling-LM-7B-alpha,8.09,0.639,2023/11,CC-BY-NC-4.0,UC Berkeley,https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha
34
- pplx-70b-online,pplx-70b-online,-,-,Online,Proprietary,Perplexity AI,https://blog.perplexity.ai/blog/introducing-pplx-online-llms
35
- openchat-3.5,OpenChat-3.5,7.81,0.643,2023/11,Apache-2.0,OpenChat,https://huggingface.co/openchat/openchat_3.5
36
- openhermes-2.5-mistral-7b,OpenHermes-2.5-Mistral-7b,-,-,2023/11,Apache-2.0,NousResearch,https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B
37
- gpt-3.5-turbo-1106,GPT-3.5-Turbo-1106,8.32,-,2021/9,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-3-5
38
- llama-2-70b-chat,Llama-2-70b-chat,6.86,0.630,2023/7,Llama 2 Community,Meta,https://huggingface.co/meta-llama/Llama-2-70b-chat-hf
39
- solar-10.7b-instruct-v1.0,SOLAR-10.7B-Instruct-v1.0,7.58,0.662,2023/11,CC-BY-NC-4.0,Upstage AI,https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0
40
- dolphin-2.2.1-mistral-7b,Dolphin-2.2.1-Mistral-7B,-,-,2023/10,Apache-2.0,Cognitive Computations,https://huggingface.co/ehartford/dolphin-2.2.1-mistral-7b
41
- wizardlm-13b,WizardLM-13b-v1.2,7.20,0.527,2023/7,Llama 2 Community,Microsoft,https://huggingface.co/WizardLM/WizardLM-13B-V1.2
42
- zephyr-7b-beta,Zephyr-7b-beta,7.34,0.614,2023/10,MIT,HuggingFace,https://huggingface.co/HuggingFaceH4/zephyr-7b-beta
43
- mpt-30b-chat,MPT-30B-chat,6.39,0.504,2023/6,CC-BY-NC-SA-4.0,MosaicML,https://huggingface.co/mosaicml/mpt-30b-chat
44
- vicuna-13b,Vicuna-13B,6.57,0.558,2023/7,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-13b-v1.5
45
- qwen-14b-chat,Qwen-14B-Chat,6.96,0.665,2023/8,Qianwen LICENSE,Alibaba,https://huggingface.co/Qwen/Qwen-14B-Chat
46
- zephyr-7b-alpha,Zephyr-7b-alpha,6.88,-,2023/10,MIT,HuggingFace,https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha
47
- codellama-34b-instruct,CodeLlama-34B-instruct,-,0.537,2023/7,Llama 2 Community,Meta,https://huggingface.co/codellama/CodeLlama-34b-Instruct-hf
48
- falcon-180b-chat,falcon-180b-chat,-,0.680,2023/9,Falcon-180B TII License,TII,https://huggingface.co/tiiuae/falcon-180B-chat
49
- guanaco-33b,Guanaco-33B,6.53,0.576,2023/5,Non-commercial,UW,https://huggingface.co/timdettmers/guanaco-33b-merged
50
- llama-2-13b-chat,Llama-2-13b-chat,6.65,0.536,2023/7,Llama 2 Community,Meta,https://huggingface.co/meta-llama/Llama-2-13b-chat-hf
51
- mistral-7b-instruct,Mistral-7B-Instruct-v0.1,6.84,0.554,2023/9,Apache 2.0,Mistral,https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1
52
- pplx-7b-online,pplx-7b-online,-,-,Online,Proprietary,Perplexity AI,https://blog.perplexity.ai/blog/introducing-pplx-online-llms
53
- llama-2-7b-chat,Llama-2-7b-chat,6.27,0.458,2023/7,Llama 2 Community,Meta,https://huggingface.co/meta-llama/Llama-2-7b-chat-hf
54
- vicuna-7b,Vicuna-7B,6.17,0.498,2023/7,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-7b-v1.5
55
- palm-2,PaLM-Chat-Bison-001,6.40,-,2021/6,Proprietary,Google,https://cloud.google.com/vertex-ai/docs/generative-ai/learn/models#foundation_models
56
- koala-13b,Koala-13B,5.35,0.447,2023/4,Non-commercial,UC Berkeley,https://bair.berkeley.edu/blog/2023/04/03/koala/
57
- chatglm3-6b,ChatGLM3-6B,-,-,2023/10,Apache-2.0,Tsinghua,https://huggingface.co/THUDM/chatglm3-6b
58
- gpt4all-13b-snoozy,GPT4All-13B-Snoozy,5.41,0.430,2023/3,Non-commercial,Nomic AI,https://huggingface.co/nomic-ai/gpt4all-13b-snoozy
59
- mpt-7b-chat,MPT-7B-Chat,5.42,0.320,2023/5,CC-BY-NC-SA-4.0,MosaicML,https://huggingface.co/mosaicml/mpt-7b-chat
60
- chatglm2-6b,ChatGLM2-6B,4.96,0.455,2023/6,Apache-2.0,Tsinghua,https://huggingface.co/THUDM/chatglm2-6b
61
- RWKV-4-Raven-14B,RWKV-4-Raven-14B,3.98,0.256,2023/4,Apache 2.0,RWKV,https://huggingface.co/BlinkDL/rwkv-4-raven
62
- alpaca-13b,Alpaca-13B,4.53,0.481,2023/3,Non-commercial,Stanford,https://crfm.stanford.edu/2023/03/13/alpaca.html
63
- oasst-pythia-12b,OpenAssistant-Pythia-12B,4.32,0.270,2023/4,Apache 2.0,OpenAssistant,https://huggingface.co/OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5
64
- chatglm-6b,ChatGLM-6B,4.50,0.361,2023/3,Non-commercial,Tsinghua,https://huggingface.co/THUDM/chatglm-6b
65
- fastchat-t5-3b,FastChat-T5-3B,3.04,0.477,2023/4,Apache 2.0,LMSYS,https://huggingface.co/lmsys/fastchat-t5-3b-v1.0
66
- stablelm-tuned-alpha-7b,StableLM-Tuned-Alpha-7B,2.75,0.244,2023/4,CC-BY-NC-SA-4.0,Stability AI,https://huggingface.co/stabilityai/stablelm-tuned-alpha-7b
67
- dolly-v2-12b,Dolly-V2-12B,3.28,0.257,2023/4,MIT,Databricks,https://huggingface.co/databricks/dolly-v2-12b
68
- llama-13b,LLaMA-13B,2.61,0.470,2023/2,Non-commercial,Meta,https://arxiv.org/abs/2302.13971
69
- mistral-medium,Mistral Medium,8.61,0.753,-,Proprietary,Mistral,https://mistral.ai/news/la-plateforme/
70
- llama2-70b-steerlm-chat,NV-Llama2-70B-SteerLM-Chat,7.54,0.685,2023/11,Llama 2 Community,Nvidia,https://huggingface.co/nvidia/Llama2-70B-SteerLM-Chat
71
- stripedhyena-nous-7b,StripedHyena-Nous-7B,-,-,2023/12,Apache 2.0,Together AI,https://huggingface.co/togethercomputer/StripedHyena-Nous-7B
72
- deepseek-llm-67b-chat,DeepSeek-LLM-67B-Chat,-,0.713,2023/11,DeepSeek License,DeepSeek AI,https://huggingface.co/deepseek-ai/deepseek-llm-67b-chat
73
- gpt-4-0125-preview,GPT-4-0125-preview,-,-,2023/4,Proprietary,OpenAI,https://openai.com/blog/new-models-and-developer-products-announced-at-devday
74
- qwen1.5-72b-chat,Qwen1.5-72B-Chat,8.61,0.775,2024/2,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen1.5/
75
- qwen1.5-7b-chat,Qwen1.5-7B-Chat,7.6,0.610,2024/2,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen1.5/
76
- qwen1.5-4b-chat,Qwen1.5-4B-Chat,-,0.561,2024/2,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen1.5/
77
- openchat-3.5-0106,OpenChat-3.5-0106,7.8,0.658,2024/1,Apache-2.0,OpenChat,https://huggingface.co/openchat/openchat-3.5-0106
78
- nous-hermes-2-mixtral-8x7b-dpo,Nous-Hermes-2-Mixtral-8x7B-DPO,-,-,2024/1,Apache-2.0,NousResearch,https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO
79
- gpt-3.5-turbo-0125,GPT-3.5-Turbo-0125,-,-,2021/9,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-3-5-turbo
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
leaderboard_table_20240305.csv DELETED
@@ -1,84 +0,0 @@
1
- key,Model,MT-bench (score),MMLU,Knowledge cutoff date,License,Organization,Link
2
- wizardlm-30b,WizardLM-30B,7.01,0.587,2023/6,Non-commercial,Microsoft,https://huggingface.co/WizardLM/WizardLM-30B-V1.0
3
- vicuna-13b-16k,Vicuna-13B-16k,6.92,0.545,2023/7,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-13b-v1.5-16k
4
- wizardlm-13b-v1.1,WizardLM-13B-v1.1,6.76,0.500,2023/7,Non-commercial,Microsoft,https://huggingface.co/WizardLM/WizardLM-13B-V1.1
5
- tulu-30b,Tulu-30B,6.43,0.581,2023/6,Non-commercial,AllenAI/UW,https://huggingface.co/allenai/tulu-30b
6
- guanaco-65b,Guanaco-65B,6.41,0.621,2023/5,Non-commercial,UW,https://huggingface.co/timdettmers/guanaco-65b-merged
7
- openassistant-llama-30b,OpenAssistant-LLaMA-30B,6.41,0.560,2023/4,Non-commercial,OpenAssistant,https://huggingface.co/OpenAssistant/oasst-sft-6-llama-30b-xor
8
- wizardlm-13b-v1.0,WizardLM-13B-v1.0,6.35,0.523,2023/5,Non-commercial,Microsoft,https://huggingface.co/WizardLM/WizardLM-13B-V1.0
9
- vicuna-7b-16k,Vicuna-7B-16k,6.22,0.485,2023/7,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-7b-v1.5-16k
10
- baize-v2-13b,Baize-v2-13B,5.75,0.489,2023/4,Non-commercial,UCSD,https://huggingface.co/project-baize/baize-v2-13b
11
- xgen-7b-8k-inst,XGen-7B-8K-Inst,5.55,0.421,2023/7,Non-commercial,Salesforce,https://huggingface.co/Salesforce/xgen-7b-8k-inst
12
- nous-hermes-13b,Nous-Hermes-13B,5.51,0.493,2023/6,Non-commercial,NousResearch,https://huggingface.co/NousResearch/Nous-Hermes-13b
13
- mpt-30b-instruct,MPT-30B-Instruct,5.22,0.478,2023/6,CC-BY-SA 3.0,MosaicML,https://huggingface.co/mosaicml/mpt-30b-instruct
14
- falcon-40b-instruct,Falcon-40B-Instruct,5.17,0.547,2023/5,Apache 2.0,TII,https://huggingface.co/tiiuae/falcon-40b-instruct
15
- h2o-oasst-openllama-13b,H2O-Oasst-OpenLLaMA-13B,4.63,0.428,2023/6,Apache 2.0,h2oai,https://huggingface.co/h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-13b
16
- gpt-4-1106-preview,GPT-4-1106-preview,9.32,-,2023/4,Proprietary,OpenAI,https://openai.com/blog/new-models-and-developer-products-announced-at-devday
17
- gpt-4-0314,GPT-4-0314,8.96,0.864,2021/9,Proprietary,OpenAI,https://openai.com/research/gpt-4
18
- claude-1,Claude-1,7.90,0.770,-,Proprietary,Anthropic,https://www.anthropic.com/index/introducing-claude
19
- gpt-4-0613,GPT-4-0613,9.18,-,2021/9,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo
20
- claude-2.0,Claude-2.0,8.06,0.785,-,Proprietary,Anthropic,https://www.anthropic.com/index/claude-2
21
- claude-2.1,Claude-2.1,8.18,-,-,Proprietary,Anthropic,https://www.anthropic.com/index/claude-2-1
22
- gpt-3.5-turbo-0613,GPT-3.5-Turbo-0613,8.39,-,2021/9,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-3-5
23
- mixtral-8x7b-instruct-v0.1,Mixtral-8x7b-Instruct-v0.1,8.30,0.706,2023/12,Apache 2.0,Mistral,https://mistral.ai/news/mixtral-of-experts/
24
- claude-instant-1,Claude-Instant-1,7.85,0.734,-,Proprietary,Anthropic,https://www.anthropic.com/index/introducing-claude
25
- gpt-3.5-turbo-0314,GPT-3.5-Turbo-0314,7.94,0.700,2021/9,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-3-5
26
- tulu-2-dpo-70b,Tulu-2-DPO-70B,7.89,-,2023/11,AI2 ImpACT Low-risk,AllenAI/UW,https://huggingface.co/allenai/tulu-2-dpo-70b
27
- yi-34b-chat,Yi-34B-Chat,-,0.735,2023/6,Yi License,01 AI,https://huggingface.co/01-ai/Yi-34B-Chat
28
- gemini-pro,Gemini Pro,-,0.718,2023/4,Proprietary,Google,https://blog.google/technology/ai/gemini-api-developers-cloud/
29
- gemini-pro-dev-api,Gemini Pro (Dev API),-,0.718,2023/4,Proprietary,Google,https://ai.google.dev/docs/gemini_api_overview
30
- bard-jan-24-gemini-pro,Bard (Gemini Pro),-,-,Online,Proprietary,Google,https://bard.google.com/
31
- wizardlm-70b,WizardLM-70B-v1.0,7.71,0.637,2023/8,Llama 2 Community,Microsoft,https://huggingface.co/WizardLM/WizardLM-70B-V1.0
32
- vicuna-33b,Vicuna-33B,7.12,0.592,2023/8,Non-commercial,LMSYS,https://huggingface.co/lmsys/vicuna-33b-v1.3
33
- starling-lm-7b-alpha,Starling-LM-7B-alpha,8.09,0.639,2023/11,CC-BY-NC-4.0,UC Berkeley,https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha
34
- pplx-70b-online,pplx-70b-online,-,-,Online,Proprietary,Perplexity AI,https://blog.perplexity.ai/blog/introducing-pplx-online-llms
35
- openchat-3.5,OpenChat-3.5,7.81,0.643,2023/11,Apache-2.0,OpenChat,https://huggingface.co/openchat/openchat_3.5
36
- openhermes-2.5-mistral-7b,OpenHermes-2.5-Mistral-7b,-,-,2023/11,Apache-2.0,NousResearch,https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B
37
- gpt-3.5-turbo-1106,GPT-3.5-Turbo-1106,8.32,-,2021/9,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-3-5
38
- llama-2-70b-chat,Llama-2-70b-chat,6.86,0.630,2023/7,Llama 2 Community,Meta,https://huggingface.co/meta-llama/Llama-2-70b-chat-hf
39
- solar-10.7b-instruct-v1.0,SOLAR-10.7B-Instruct-v1.0,7.58,0.662,2023/11,CC-BY-NC-4.0,Upstage AI,https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0
40
- dolphin-2.2.1-mistral-7b,Dolphin-2.2.1-Mistral-7B,-,-,2023/10,Apache-2.0,Cognitive Computations,https://huggingface.co/ehartford/dolphin-2.2.1-mistral-7b
41
- wizardlm-13b,WizardLM-13b-v1.2,7.20,0.527,2023/7,Llama 2 Community,Microsoft,https://huggingface.co/WizardLM/WizardLM-13B-V1.2
42
- zephyr-7b-beta,Zephyr-7b-beta,7.34,0.614,2023/10,MIT,HuggingFace,https://huggingface.co/HuggingFaceH4/zephyr-7b-beta
43
- mpt-30b-chat,MPT-30B-chat,6.39,0.504,2023/6,CC-BY-NC-SA-4.0,MosaicML,https://huggingface.co/mosaicml/mpt-30b-chat
44
- vicuna-13b,Vicuna-13B,6.57,0.558,2023/7,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-13b-v1.5
45
- qwen-14b-chat,Qwen-14B-Chat,6.96,0.665,2023/8,Qianwen LICENSE,Alibaba,https://huggingface.co/Qwen/Qwen-14B-Chat
46
- zephyr-7b-alpha,Zephyr-7b-alpha,6.88,-,2023/10,MIT,HuggingFace,https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha
47
- codellama-34b-instruct,CodeLlama-34B-instruct,-,0.537,2023/7,Llama 2 Community,Meta,https://huggingface.co/codellama/CodeLlama-34b-Instruct-hf
48
- falcon-180b-chat,falcon-180b-chat,-,0.680,2023/9,Falcon-180B TII License,TII,https://huggingface.co/tiiuae/falcon-180B-chat
49
- guanaco-33b,Guanaco-33B,6.53,0.576,2023/5,Non-commercial,UW,https://huggingface.co/timdettmers/guanaco-33b-merged
50
- llama-2-13b-chat,Llama-2-13b-chat,6.65,0.536,2023/7,Llama 2 Community,Meta,https://huggingface.co/meta-llama/Llama-2-13b-chat-hf
51
- mistral-7b-instruct,Mistral-7B-Instruct-v0.1,6.84,0.554,2023/9,Apache 2.0,Mistral,https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1
52
- pplx-7b-online,pplx-7b-online,-,-,Online,Proprietary,Perplexity AI,https://blog.perplexity.ai/blog/introducing-pplx-online-llms
53
- llama-2-7b-chat,Llama-2-7b-chat,6.27,0.458,2023/7,Llama 2 Community,Meta,https://huggingface.co/meta-llama/Llama-2-7b-chat-hf
54
- vicuna-7b,Vicuna-7B,6.17,0.498,2023/7,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-7b-v1.5
55
- palm-2,PaLM-Chat-Bison-001,6.40,-,2021/6,Proprietary,Google,https://cloud.google.com/vertex-ai/docs/generative-ai/learn/models#foundation_models
56
- koala-13b,Koala-13B,5.35,0.447,2023/4,Non-commercial,UC Berkeley,https://bair.berkeley.edu/blog/2023/04/03/koala/
57
- chatglm3-6b,ChatGLM3-6B,-,-,2023/10,Apache-2.0,Tsinghua,https://huggingface.co/THUDM/chatglm3-6b
58
- gpt4all-13b-snoozy,GPT4All-13B-Snoozy,5.41,0.430,2023/3,Non-commercial,Nomic AI,https://huggingface.co/nomic-ai/gpt4all-13b-snoozy
59
- mpt-7b-chat,MPT-7B-Chat,5.42,0.320,2023/5,CC-BY-NC-SA-4.0,MosaicML,https://huggingface.co/mosaicml/mpt-7b-chat
60
- chatglm2-6b,ChatGLM2-6B,4.96,0.455,2023/6,Apache-2.0,Tsinghua,https://huggingface.co/THUDM/chatglm2-6b
61
- RWKV-4-Raven-14B,RWKV-4-Raven-14B,3.98,0.256,2023/4,Apache 2.0,RWKV,https://huggingface.co/BlinkDL/rwkv-4-raven
62
- alpaca-13b,Alpaca-13B,4.53,0.481,2023/3,Non-commercial,Stanford,https://crfm.stanford.edu/2023/03/13/alpaca.html
63
- oasst-pythia-12b,OpenAssistant-Pythia-12B,4.32,0.270,2023/4,Apache 2.0,OpenAssistant,https://huggingface.co/OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5
64
- chatglm-6b,ChatGLM-6B,4.50,0.361,2023/3,Non-commercial,Tsinghua,https://huggingface.co/THUDM/chatglm-6b
65
- fastchat-t5-3b,FastChat-T5-3B,3.04,0.477,2023/4,Apache 2.0,LMSYS,https://huggingface.co/lmsys/fastchat-t5-3b-v1.0
66
- stablelm-tuned-alpha-7b,StableLM-Tuned-Alpha-7B,2.75,0.244,2023/4,CC-BY-NC-SA-4.0,Stability AI,https://huggingface.co/stabilityai/stablelm-tuned-alpha-7b
67
- dolly-v2-12b,Dolly-V2-12B,3.28,0.257,2023/4,MIT,Databricks,https://huggingface.co/databricks/dolly-v2-12b
68
- llama-13b,LLaMA-13B,2.61,0.470,2023/2,Non-commercial,Meta,https://arxiv.org/abs/2302.13971
69
- mistral-medium,Mistral Medium,8.61,0.753,-,Proprietary,Mistral,https://mistral.ai/news/la-plateforme/
70
- llama2-70b-steerlm-chat,NV-Llama2-70B-SteerLM-Chat,7.54,0.685,2023/11,Llama 2 Community,Nvidia,https://huggingface.co/nvidia/Llama2-70B-SteerLM-Chat
71
- stripedhyena-nous-7b,StripedHyena-Nous-7B,-,-,2023/12,Apache 2.0,Together AI,https://huggingface.co/togethercomputer/StripedHyena-Nous-7B
72
- deepseek-llm-67b-chat,DeepSeek-LLM-67B-Chat,-,0.713,2023/11,DeepSeek License,DeepSeek AI,https://huggingface.co/deepseek-ai/deepseek-llm-67b-chat
73
- gpt-4-0125-preview,GPT-4-0125-preview,-,-,2023/12,Proprietary,OpenAI,https://openai.com/blog/new-models-and-developer-products-announced-at-devday
74
- qwen1.5-72b-chat,Qwen1.5-72B-Chat,8.61,0.775,2024/2,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen1.5/
75
- qwen1.5-7b-chat,Qwen1.5-7B-Chat,7.6,0.610,2024/2,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen1.5/
76
- qwen1.5-4b-chat,Qwen1.5-4B-Chat,-,0.561,2024/2,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen1.5/
77
- openchat-3.5-0106,OpenChat-3.5-0106,7.8,0.658,2024/1,Apache-2.0,OpenChat,https://huggingface.co/openchat/openchat-3.5-0106
78
- nous-hermes-2-mixtral-8x7b-dpo,Nous-Hermes-2-Mixtral-8x7B-DPO,-,-,2024/1,Apache-2.0,NousResearch,https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO
79
- gpt-3.5-turbo-0125,GPT-3.5-Turbo-0125,-,-,2021/9,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-3-5-turbo
80
- mistral-next,Mistral-Next,-,-,-,Proprietary,Mistral,https://chat.mistral.ai/chat
81
- mistral-large-2402,Mistral-Large-2402,-,0.812,-,Proprietary,Mistral,https://mistral.ai/news/mistral-large/
82
- gemma-7b-it,Gemma-7B-it,-,0.643,2024/2,Gemma license,Google,https://huggingface.co/google/gemma-7b-it
83
- gemma-2b-it,Gemma-2B-it,-,0.423,2024/2,Gemma license,Google,https://huggingface.co/google/gemma-2b-it
84
- mistral-7b-instruct-v0.2,Mistral-7B-Instruct-v0.2,7.6,-,2023/12,Apache-2.0,Mistral,https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
leaderboard_table_20240307.csv DELETED
@@ -1,88 +0,0 @@
1
- key,Model,MT-bench (score),MMLU,Knowledge cutoff date,License,Organization,Link
2
- wizardlm-30b,WizardLM-30B,7.01,0.587,2023/6,Non-commercial,Microsoft,https://huggingface.co/WizardLM/WizardLM-30B-V1.0
3
- vicuna-13b-16k,Vicuna-13B-16k,6.92,0.545,2023/7,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-13b-v1.5-16k
4
- wizardlm-13b-v1.1,WizardLM-13B-v1.1,6.76,0.500,2023/7,Non-commercial,Microsoft,https://huggingface.co/WizardLM/WizardLM-13B-V1.1
5
- tulu-30b,Tulu-30B,6.43,0.581,2023/6,Non-commercial,AllenAI/UW,https://huggingface.co/allenai/tulu-30b
6
- guanaco-65b,Guanaco-65B,6.41,0.621,2023/5,Non-commercial,UW,https://huggingface.co/timdettmers/guanaco-65b-merged
7
- openassistant-llama-30b,OpenAssistant-LLaMA-30B,6.41,0.560,2023/4,Non-commercial,OpenAssistant,https://huggingface.co/OpenAssistant/oasst-sft-6-llama-30b-xor
8
- wizardlm-13b-v1.0,WizardLM-13B-v1.0,6.35,0.523,2023/5,Non-commercial,Microsoft,https://huggingface.co/WizardLM/WizardLM-13B-V1.0
9
- vicuna-7b-16k,Vicuna-7B-16k,6.22,0.485,2023/7,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-7b-v1.5-16k
10
- baize-v2-13b,Baize-v2-13B,5.75,0.489,2023/4,Non-commercial,UCSD,https://huggingface.co/project-baize/baize-v2-13b
11
- xgen-7b-8k-inst,XGen-7B-8K-Inst,5.55,0.421,2023/7,Non-commercial,Salesforce,https://huggingface.co/Salesforce/xgen-7b-8k-inst
12
- nous-hermes-13b,Nous-Hermes-13B,5.51,0.493,2023/6,Non-commercial,NousResearch,https://huggingface.co/NousResearch/Nous-Hermes-13b
13
- mpt-30b-instruct,MPT-30B-Instruct,5.22,0.478,2023/6,CC-BY-SA 3.0,MosaicML,https://huggingface.co/mosaicml/mpt-30b-instruct
14
- falcon-40b-instruct,Falcon-40B-Instruct,5.17,0.547,2023/5,Apache 2.0,TII,https://huggingface.co/tiiuae/falcon-40b-instruct
15
- h2o-oasst-openllama-13b,H2O-Oasst-OpenLLaMA-13B,4.63,0.428,2023/6,Apache 2.0,h2oai,https://huggingface.co/h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-13b
16
- gpt-4-1106-preview,GPT-4-1106-preview,9.32,-,2023/4,Proprietary,OpenAI,https://openai.com/blog/new-models-and-developer-products-announced-at-devday
17
- gpt-4-0314,GPT-4-0314,8.96,0.864,2021/9,Proprietary,OpenAI,https://openai.com/research/gpt-4
18
- claude-1,Claude-1,7.90,0.770,-,Proprietary,Anthropic,https://www.anthropic.com/index/introducing-claude
19
- gpt-4-0613,GPT-4-0613,9.18,-,2021/9,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo
20
- claude-2.0,Claude-2.0,8.06,0.785,-,Proprietary,Anthropic,https://www.anthropic.com/index/claude-2
21
- claude-2.1,Claude-2.1,8.18,-,-,Proprietary,Anthropic,https://www.anthropic.com/index/claude-2-1
22
- gpt-3.5-turbo-0613,GPT-3.5-Turbo-0613,8.39,-,2021/9,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-3-5
23
- mixtral-8x7b-instruct-v0.1,Mixtral-8x7b-Instruct-v0.1,8.30,0.706,2023/12,Apache 2.0,Mistral,https://mistral.ai/news/mixtral-of-experts/
24
- claude-instant-1,Claude-Instant-1,7.85,0.734,-,Proprietary,Anthropic,https://www.anthropic.com/index/introducing-claude
25
- gpt-3.5-turbo-0314,GPT-3.5-Turbo-0314,7.94,0.700,2021/9,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-3-5
26
- tulu-2-dpo-70b,Tulu-2-DPO-70B,7.89,-,2023/11,AI2 ImpACT Low-risk,AllenAI/UW,https://huggingface.co/allenai/tulu-2-dpo-70b
27
- yi-34b-chat,Yi-34B-Chat,-,0.735,2023/6,Yi License,01 AI,https://huggingface.co/01-ai/Yi-34B-Chat
28
- gemini-pro,Gemini Pro,-,0.718,2023/4,Proprietary,Google,https://blog.google/technology/ai/gemini-api-developers-cloud/
29
- gemini-pro-dev-api,Gemini Pro (Dev API),-,0.718,2023/4,Proprietary,Google,https://ai.google.dev/docs/gemini_api_overview
30
- bard-jan-24-gemini-pro,Bard (Gemini Pro),-,-,Online,Proprietary,Google,https://bard.google.com/
31
- wizardlm-70b,WizardLM-70B-v1.0,7.71,0.637,2023/8,Llama 2 Community,Microsoft,https://huggingface.co/WizardLM/WizardLM-70B-V1.0
32
- vicuna-33b,Vicuna-33B,7.12,0.592,2023/8,Non-commercial,LMSYS,https://huggingface.co/lmsys/vicuna-33b-v1.3
33
- starling-lm-7b-alpha,Starling-LM-7B-alpha,8.09,0.639,2023/11,CC-BY-NC-4.0,UC Berkeley,https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha
34
- pplx-70b-online,pplx-70b-online,-,-,Online,Proprietary,Perplexity AI,https://blog.perplexity.ai/blog/introducing-pplx-online-llms
35
- openchat-3.5,OpenChat-3.5,7.81,0.643,2023/11,Apache-2.0,OpenChat,https://huggingface.co/openchat/openchat_3.5
36
- openhermes-2.5-mistral-7b,OpenHermes-2.5-Mistral-7b,-,-,2023/11,Apache-2.0,NousResearch,https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B
37
- gpt-3.5-turbo-1106,GPT-3.5-Turbo-1106,8.32,-,2021/9,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-3-5
38
- llama-2-70b-chat,Llama-2-70b-chat,6.86,0.630,2023/7,Llama 2 Community,Meta,https://huggingface.co/meta-llama/Llama-2-70b-chat-hf
39
- solar-10.7b-instruct-v1.0,SOLAR-10.7B-Instruct-v1.0,7.58,0.662,2023/11,CC-BY-NC-4.0,Upstage AI,https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0
40
- dolphin-2.2.1-mistral-7b,Dolphin-2.2.1-Mistral-7B,-,-,2023/10,Apache-2.0,Cognitive Computations,https://huggingface.co/ehartford/dolphin-2.2.1-mistral-7b
41
- wizardlm-13b,WizardLM-13b-v1.2,7.20,0.527,2023/7,Llama 2 Community,Microsoft,https://huggingface.co/WizardLM/WizardLM-13B-V1.2
42
- zephyr-7b-beta,Zephyr-7b-beta,7.34,0.614,2023/10,MIT,HuggingFace,https://huggingface.co/HuggingFaceH4/zephyr-7b-beta
43
- mpt-30b-chat,MPT-30B-chat,6.39,0.504,2023/6,CC-BY-NC-SA-4.0,MosaicML,https://huggingface.co/mosaicml/mpt-30b-chat
44
- vicuna-13b,Vicuna-13B,6.57,0.558,2023/7,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-13b-v1.5
45
- qwen-14b-chat,Qwen-14B-Chat,6.96,0.665,2023/8,Qianwen LICENSE,Alibaba,https://huggingface.co/Qwen/Qwen-14B-Chat
46
- zephyr-7b-alpha,Zephyr-7b-alpha,6.88,-,2023/10,MIT,HuggingFace,https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha
47
- codellama-34b-instruct,CodeLlama-34B-instruct,-,0.537,2023/7,Llama 2 Community,Meta,https://huggingface.co/codellama/CodeLlama-34b-Instruct-hf
48
- falcon-180b-chat,falcon-180b-chat,-,0.680,2023/9,Falcon-180B TII License,TII,https://huggingface.co/tiiuae/falcon-180B-chat
49
- guanaco-33b,Guanaco-33B,6.53,0.576,2023/5,Non-commercial,UW,https://huggingface.co/timdettmers/guanaco-33b-merged
50
- llama-2-13b-chat,Llama-2-13b-chat,6.65,0.536,2023/7,Llama 2 Community,Meta,https://huggingface.co/meta-llama/Llama-2-13b-chat-hf
51
- mistral-7b-instruct,Mistral-7B-Instruct-v0.1,6.84,0.554,2023/9,Apache 2.0,Mistral,https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1
52
- pplx-7b-online,pplx-7b-online,-,-,Online,Proprietary,Perplexity AI,https://blog.perplexity.ai/blog/introducing-pplx-online-llms
53
- llama-2-7b-chat,Llama-2-7b-chat,6.27,0.458,2023/7,Llama 2 Community,Meta,https://huggingface.co/meta-llama/Llama-2-7b-chat-hf
54
- vicuna-7b,Vicuna-7B,6.17,0.498,2023/7,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-7b-v1.5
55
- palm-2,PaLM-Chat-Bison-001,6.40,-,2021/6,Proprietary,Google,https://cloud.google.com/vertex-ai/docs/generative-ai/learn/models#foundation_models
56
- koala-13b,Koala-13B,5.35,0.447,2023/4,Non-commercial,UC Berkeley,https://bair.berkeley.edu/blog/2023/04/03/koala/
57
- chatglm3-6b,ChatGLM3-6B,-,-,2023/10,Apache-2.0,Tsinghua,https://huggingface.co/THUDM/chatglm3-6b
58
- gpt4all-13b-snoozy,GPT4All-13B-Snoozy,5.41,0.430,2023/3,Non-commercial,Nomic AI,https://huggingface.co/nomic-ai/gpt4all-13b-snoozy
59
- mpt-7b-chat,MPT-7B-Chat,5.42,0.320,2023/5,CC-BY-NC-SA-4.0,MosaicML,https://huggingface.co/mosaicml/mpt-7b-chat
60
- chatglm2-6b,ChatGLM2-6B,4.96,0.455,2023/6,Apache-2.0,Tsinghua,https://huggingface.co/THUDM/chatglm2-6b
61
- RWKV-4-Raven-14B,RWKV-4-Raven-14B,3.98,0.256,2023/4,Apache 2.0,RWKV,https://huggingface.co/BlinkDL/rwkv-4-raven
62
- alpaca-13b,Alpaca-13B,4.53,0.481,2023/3,Non-commercial,Stanford,https://crfm.stanford.edu/2023/03/13/alpaca.html
63
- oasst-pythia-12b,OpenAssistant-Pythia-12B,4.32,0.270,2023/4,Apache 2.0,OpenAssistant,https://huggingface.co/OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5
64
- chatglm-6b,ChatGLM-6B,4.50,0.361,2023/3,Non-commercial,Tsinghua,https://huggingface.co/THUDM/chatglm-6b
65
- fastchat-t5-3b,FastChat-T5-3B,3.04,0.477,2023/4,Apache 2.0,LMSYS,https://huggingface.co/lmsys/fastchat-t5-3b-v1.0
66
- stablelm-tuned-alpha-7b,StableLM-Tuned-Alpha-7B,2.75,0.244,2023/4,CC-BY-NC-SA-4.0,Stability AI,https://huggingface.co/stabilityai/stablelm-tuned-alpha-7b
67
- dolly-v2-12b,Dolly-V2-12B,3.28,0.257,2023/4,MIT,Databricks,https://huggingface.co/databricks/dolly-v2-12b
68
- llama-13b,LLaMA-13B,2.61,0.470,2023/2,Non-commercial,Meta,https://arxiv.org/abs/2302.13971
69
- mistral-medium,Mistral Medium,8.61,0.753,-,Proprietary,Mistral,https://mistral.ai/news/la-plateforme/
70
- llama2-70b-steerlm-chat,NV-Llama2-70B-SteerLM-Chat,7.54,0.685,2023/11,Llama 2 Community,Nvidia,https://huggingface.co/nvidia/Llama2-70B-SteerLM-Chat
71
- stripedhyena-nous-7b,StripedHyena-Nous-7B,-,-,2023/12,Apache 2.0,Together AI,https://huggingface.co/togethercomputer/StripedHyena-Nous-7B
72
- deepseek-llm-67b-chat,DeepSeek-LLM-67B-Chat,-,0.713,2023/11,DeepSeek License,DeepSeek AI,https://huggingface.co/deepseek-ai/deepseek-llm-67b-chat
73
- gpt-4-0125-preview,GPT-4-0125-preview,-,-,2023/12,Proprietary,OpenAI,https://openai.com/blog/new-models-and-developer-products-announced-at-devday
74
- qwen1.5-72b-chat,Qwen1.5-72B-Chat,8.61,0.775,2024/2,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen1.5/
75
- qwen1.5-7b-chat,Qwen1.5-7B-Chat,7.6,0.610,2024/2,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen1.5/
76
- qwen1.5-4b-chat,Qwen1.5-4B-Chat,-,0.561,2024/2,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen1.5/
77
- openchat-3.5-0106,OpenChat-3.5-0106,7.8,0.658,2024/1,Apache-2.0,OpenChat,https://huggingface.co/openchat/openchat-3.5-0106
78
- nous-hermes-2-mixtral-8x7b-dpo,Nous-Hermes-2-Mixtral-8x7B-DPO,-,-,2024/1,Apache-2.0,NousResearch,https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO
79
- gpt-3.5-turbo-0125,GPT-3.5-Turbo-0125,-,-,2021/9,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-3-5-turbo
80
- mistral-next,Mistral-Next,-,-,-,Proprietary,Mistral,https://chat.mistral.ai/chat
81
- mistral-large-2402,Mistral-Large-2402,-,0.812,-,Proprietary,Mistral,https://mistral.ai/news/mistral-large/
82
- gemma-7b-it,Gemma-7B-it,-,0.643,2024/2,Gemma license,Google,https://huggingface.co/google/gemma-7b-it
83
- gemma-2b-it,Gemma-2B-it,-,0.423,2024/2,Gemma license,Google,https://huggingface.co/google/gemma-2b-it
84
- mistral-7b-instruct-v0.2,Mistral-7B-Instruct-v0.2,7.6,-,2023/12,Apache-2.0,Mistral,https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2
85
- claude-3-sonnet-20240229,Claude 3 Sonnet,-,0.790,2023/8,Proprietary,Anthropic,https://www.anthropic.com/news/claude-3-family
86
- claude-3-opus-20240229,Claude 3 Opus,-,0.868,2023/8,Proprietary,Anthropic,https://www.anthropic.com/news/claude-3-family
87
- codellama-70b-instruct,CodeLlama-70B-instruct,-,-,2024/1,Llama 2 Community,Meta,https://huggingface.co/codellama/CodeLlama-70b-hf
88
- olmo-7b-instruct,OLMo-7B-instruct,-,-,2024/2,Apache-2.0,Allen AI,https://huggingface.co/allenai/OLMo-7B-Instruct
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
leaderboard_table_20240313.csv DELETED
@@ -1,88 +0,0 @@
1
- key,Model,MT-bench (score),MMLU,Knowledge cutoff date,License,Organization,Link
2
- wizardlm-30b,WizardLM-30B,7.01,0.587,2023/6,Non-commercial,Microsoft,https://huggingface.co/WizardLM/WizardLM-30B-V1.0
3
- vicuna-13b-16k,Vicuna-13B-16k,6.92,0.545,2023/7,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-13b-v1.5-16k
4
- wizardlm-13b-v1.1,WizardLM-13B-v1.1,6.76,0.500,2023/7,Non-commercial,Microsoft,https://huggingface.co/WizardLM/WizardLM-13B-V1.1
5
- tulu-30b,Tulu-30B,6.43,0.581,2023/6,Non-commercial,AllenAI/UW,https://huggingface.co/allenai/tulu-30b
6
- guanaco-65b,Guanaco-65B,6.41,0.621,2023/5,Non-commercial,UW,https://huggingface.co/timdettmers/guanaco-65b-merged
7
- openassistant-llama-30b,OpenAssistant-LLaMA-30B,6.41,0.560,2023/4,Non-commercial,OpenAssistant,https://huggingface.co/OpenAssistant/oasst-sft-6-llama-30b-xor
8
- wizardlm-13b-v1.0,WizardLM-13B-v1.0,6.35,0.523,2023/5,Non-commercial,Microsoft,https://huggingface.co/WizardLM/WizardLM-13B-V1.0
9
- vicuna-7b-16k,Vicuna-7B-16k,6.22,0.485,2023/7,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-7b-v1.5-16k
10
- baize-v2-13b,Baize-v2-13B,5.75,0.489,2023/4,Non-commercial,UCSD,https://huggingface.co/project-baize/baize-v2-13b
11
- xgen-7b-8k-inst,XGen-7B-8K-Inst,5.55,0.421,2023/7,Non-commercial,Salesforce,https://huggingface.co/Salesforce/xgen-7b-8k-inst
12
- nous-hermes-13b,Nous-Hermes-13B,5.51,0.493,2023/6,Non-commercial,NousResearch,https://huggingface.co/NousResearch/Nous-Hermes-13b
13
- mpt-30b-instruct,MPT-30B-Instruct,5.22,0.478,2023/6,CC-BY-SA 3.0,MosaicML,https://huggingface.co/mosaicml/mpt-30b-instruct
14
- falcon-40b-instruct,Falcon-40B-Instruct,5.17,0.547,2023/5,Apache 2.0,TII,https://huggingface.co/tiiuae/falcon-40b-instruct
15
- h2o-oasst-openllama-13b,H2O-Oasst-OpenLLaMA-13B,4.63,0.428,2023/6,Apache 2.0,h2oai,https://huggingface.co/h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-13b
16
- gpt-4-1106-preview,GPT-4-1106-preview,9.32,-,2023/4,Proprietary,OpenAI,https://openai.com/blog/new-models-and-developer-products-announced-at-devday
17
- gpt-4-0314,GPT-4-0314,8.96,0.864,2021/9,Proprietary,OpenAI,https://openai.com/research/gpt-4
18
- claude-1,Claude-1,7.90,0.770,-,Proprietary,Anthropic,https://www.anthropic.com/index/introducing-claude
19
- gpt-4-0613,GPT-4-0613,9.18,-,2021/9,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo
20
- claude-2.0,Claude-2.0,8.06,0.785,-,Proprietary,Anthropic,https://www.anthropic.com/index/claude-2
21
- claude-2.1,Claude-2.1,8.18,-,-,Proprietary,Anthropic,https://www.anthropic.com/index/claude-2-1
22
- gpt-3.5-turbo-0613,GPT-3.5-Turbo-0613,8.39,-,2021/9,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-3-5
23
- mixtral-8x7b-instruct-v0.1,Mixtral-8x7b-Instruct-v0.1,8.30,0.706,2023/12,Apache 2.0,Mistral,https://mistral.ai/news/mixtral-of-experts/
24
- claude-instant-1,Claude-Instant-1,7.85,0.734,-,Proprietary,Anthropic,https://www.anthropic.com/index/introducing-claude
25
- gpt-3.5-turbo-0314,GPT-3.5-Turbo-0314,7.94,0.700,2021/9,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-3-5
26
- tulu-2-dpo-70b,Tulu-2-DPO-70B,7.89,-,2023/11,AI2 ImpACT Low-risk,AllenAI/UW,https://huggingface.co/allenai/tulu-2-dpo-70b
27
- yi-34b-chat,Yi-34B-Chat,-,0.735,2023/6,Yi License,01 AI,https://huggingface.co/01-ai/Yi-34B-Chat
28
- gemini-pro,Gemini Pro,-,0.718,2023/4,Proprietary,Google,https://blog.google/technology/ai/gemini-api-developers-cloud/
29
- gemini-pro-dev-api,Gemini Pro (Dev API),-,0.718,2023/4,Proprietary,Google,https://ai.google.dev/docs/gemini_api_overview
30
- bard-jan-24-gemini-pro,Bard (Gemini Pro),-,-,Online,Proprietary,Google,https://bard.google.com/
31
- wizardlm-70b,WizardLM-70B-v1.0,7.71,0.637,2023/8,Llama 2 Community,Microsoft,https://huggingface.co/WizardLM/WizardLM-70B-V1.0
32
- vicuna-33b,Vicuna-33B,7.12,0.592,2023/8,Non-commercial,LMSYS,https://huggingface.co/lmsys/vicuna-33b-v1.3
33
- starling-lm-7b-alpha,Starling-LM-7B-alpha,8.09,0.639,2023/11,CC-BY-NC-4.0,UC Berkeley,https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha
34
- pplx-70b-online,pplx-70b-online,-,-,Online,Proprietary,Perplexity AI,https://blog.perplexity.ai/blog/introducing-pplx-online-llms
35
- openchat-3.5,OpenChat-3.5,7.81,0.643,2023/11,Apache-2.0,OpenChat,https://huggingface.co/openchat/openchat_3.5
36
- openhermes-2.5-mistral-7b,OpenHermes-2.5-Mistral-7b,-,-,2023/11,Apache-2.0,NousResearch,https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B
37
- gpt-3.5-turbo-1106,GPT-3.5-Turbo-1106,8.32,-,2021/9,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-3-5
38
- llama-2-70b-chat,Llama-2-70b-chat,6.86,0.630,2023/7,Llama 2 Community,Meta,https://huggingface.co/meta-llama/Llama-2-70b-chat-hf
39
- solar-10.7b-instruct-v1.0,SOLAR-10.7B-Instruct-v1.0,7.58,0.662,2023/11,CC-BY-NC-4.0,Upstage AI,https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0
40
- dolphin-2.2.1-mistral-7b,Dolphin-2.2.1-Mistral-7B,-,-,2023/10,Apache-2.0,Cognitive Computations,https://huggingface.co/ehartford/dolphin-2.2.1-mistral-7b
41
- wizardlm-13b,WizardLM-13b-v1.2,7.20,0.527,2023/7,Llama 2 Community,Microsoft,https://huggingface.co/WizardLM/WizardLM-13B-V1.2
42
- zephyr-7b-beta,Zephyr-7b-beta,7.34,0.614,2023/10,MIT,HuggingFace,https://huggingface.co/HuggingFaceH4/zephyr-7b-beta
43
- mpt-30b-chat,MPT-30B-chat,6.39,0.504,2023/6,CC-BY-NC-SA-4.0,MosaicML,https://huggingface.co/mosaicml/mpt-30b-chat
44
- vicuna-13b,Vicuna-13B,6.57,0.558,2023/7,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-13b-v1.5
45
- qwen-14b-chat,Qwen-14B-Chat,6.96,0.665,2023/8,Qianwen LICENSE,Alibaba,https://huggingface.co/Qwen/Qwen-14B-Chat
46
- zephyr-7b-alpha,Zephyr-7b-alpha,6.88,-,2023/10,MIT,HuggingFace,https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha
47
- codellama-34b-instruct,CodeLlama-34B-instruct,-,0.537,2023/7,Llama 2 Community,Meta,https://huggingface.co/codellama/CodeLlama-34b-Instruct-hf
48
- falcon-180b-chat,falcon-180b-chat,-,0.680,2023/9,Falcon-180B TII License,TII,https://huggingface.co/tiiuae/falcon-180B-chat
49
- guanaco-33b,Guanaco-33B,6.53,0.576,2023/5,Non-commercial,UW,https://huggingface.co/timdettmers/guanaco-33b-merged
50
- llama-2-13b-chat,Llama-2-13b-chat,6.65,0.536,2023/7,Llama 2 Community,Meta,https://huggingface.co/meta-llama/Llama-2-13b-chat-hf
51
- mistral-7b-instruct,Mistral-7B-Instruct-v0.1,6.84,0.554,2023/9,Apache 2.0,Mistral,https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1
52
- pplx-7b-online,pplx-7b-online,-,-,Online,Proprietary,Perplexity AI,https://blog.perplexity.ai/blog/introducing-pplx-online-llms
53
- llama-2-7b-chat,Llama-2-7b-chat,6.27,0.458,2023/7,Llama 2 Community,Meta,https://huggingface.co/meta-llama/Llama-2-7b-chat-hf
54
- vicuna-7b,Vicuna-7B,6.17,0.498,2023/7,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-7b-v1.5
55
- palm-2,PaLM-Chat-Bison-001,6.40,-,2021/6,Proprietary,Google,https://cloud.google.com/vertex-ai/docs/generative-ai/learn/models#foundation_models
56
- koala-13b,Koala-13B,5.35,0.447,2023/4,Non-commercial,UC Berkeley,https://bair.berkeley.edu/blog/2023/04/03/koala/
57
- chatglm3-6b,ChatGLM3-6B,-,-,2023/10,Apache-2.0,Tsinghua,https://huggingface.co/THUDM/chatglm3-6b
58
- gpt4all-13b-snoozy,GPT4All-13B-Snoozy,5.41,0.430,2023/3,Non-commercial,Nomic AI,https://huggingface.co/nomic-ai/gpt4all-13b-snoozy
59
- mpt-7b-chat,MPT-7B-Chat,5.42,0.320,2023/5,CC-BY-NC-SA-4.0,MosaicML,https://huggingface.co/mosaicml/mpt-7b-chat
60
- chatglm2-6b,ChatGLM2-6B,4.96,0.455,2023/6,Apache-2.0,Tsinghua,https://huggingface.co/THUDM/chatglm2-6b
61
- RWKV-4-Raven-14B,RWKV-4-Raven-14B,3.98,0.256,2023/4,Apache 2.0,RWKV,https://huggingface.co/BlinkDL/rwkv-4-raven
62
- alpaca-13b,Alpaca-13B,4.53,0.481,2023/3,Non-commercial,Stanford,https://crfm.stanford.edu/2023/03/13/alpaca.html
63
- oasst-pythia-12b,OpenAssistant-Pythia-12B,4.32,0.270,2023/4,Apache 2.0,OpenAssistant,https://huggingface.co/OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5
64
- chatglm-6b,ChatGLM-6B,4.50,0.361,2023/3,Non-commercial,Tsinghua,https://huggingface.co/THUDM/chatglm-6b
65
- fastchat-t5-3b,FastChat-T5-3B,3.04,0.477,2023/4,Apache 2.0,LMSYS,https://huggingface.co/lmsys/fastchat-t5-3b-v1.0
66
- stablelm-tuned-alpha-7b,StableLM-Tuned-Alpha-7B,2.75,0.244,2023/4,CC-BY-NC-SA-4.0,Stability AI,https://huggingface.co/stabilityai/stablelm-tuned-alpha-7b
67
- dolly-v2-12b,Dolly-V2-12B,3.28,0.257,2023/4,MIT,Databricks,https://huggingface.co/databricks/dolly-v2-12b
68
- llama-13b,LLaMA-13B,2.61,0.470,2023/2,Non-commercial,Meta,https://arxiv.org/abs/2302.13971
69
- mistral-medium,Mistral Medium,8.61,0.753,-,Proprietary,Mistral,https://mistral.ai/news/la-plateforme/
70
- llama2-70b-steerlm-chat,NV-Llama2-70B-SteerLM-Chat,7.54,0.685,2023/11,Llama 2 Community,Nvidia,https://huggingface.co/nvidia/Llama2-70B-SteerLM-Chat
71
- stripedhyena-nous-7b,StripedHyena-Nous-7B,-,-,2023/12,Apache 2.0,Together AI,https://huggingface.co/togethercomputer/StripedHyena-Nous-7B
72
- deepseek-llm-67b-chat,DeepSeek-LLM-67B-Chat,-,0.713,2023/11,DeepSeek License,DeepSeek AI,https://huggingface.co/deepseek-ai/deepseek-llm-67b-chat
73
- gpt-4-0125-preview,GPT-4-0125-preview,-,-,2023/12,Proprietary,OpenAI,https://openai.com/blog/new-models-and-developer-products-announced-at-devday
74
- qwen1.5-72b-chat,Qwen1.5-72B-Chat,8.61,0.775,2024/2,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen1.5/
75
- qwen1.5-7b-chat,Qwen1.5-7B-Chat,7.6,0.610,2024/2,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen1.5/
76
- qwen1.5-4b-chat,Qwen1.5-4B-Chat,-,0.561,2024/2,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen1.5/
77
- openchat-3.5-0106,OpenChat-3.5-0106,7.8,0.658,2024/1,Apache-2.0,OpenChat,https://huggingface.co/openchat/openchat-3.5-0106
78
- nous-hermes-2-mixtral-8x7b-dpo,Nous-Hermes-2-Mixtral-8x7B-DPO,-,-,2024/1,Apache-2.0,NousResearch,https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO
79
- gpt-3.5-turbo-0125,GPT-3.5-Turbo-0125,-,-,2021/9,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-3-5-turbo
80
- mistral-next,Mistral-Next,-,-,-,Proprietary,Mistral,https://chat.mistral.ai/chat
81
- mistral-large-2402,Mistral-Large-2402,-,0.812,-,Proprietary,Mistral,https://mistral.ai/news/mistral-large/
82
- gemma-7b-it,Gemma-7B-it,-,0.643,2024/2,Gemma license,Google,https://huggingface.co/google/gemma-7b-it
83
- gemma-2b-it,Gemma-2B-it,-,0.423,2024/2,Gemma license,Google,https://huggingface.co/google/gemma-2b-it
84
- mistral-7b-instruct-v0.2,Mistral-7B-Instruct-v0.2,7.6,-,2023/12,Apache-2.0,Mistral,https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2
85
- claude-3-sonnet-20240229,Claude 3 Sonnet,-,0.790,2023/8,Proprietary,Anthropic,https://www.anthropic.com/news/claude-3-family
86
- claude-3-opus-20240229,Claude 3 Opus,-,0.868,2023/8,Proprietary,Anthropic,https://www.anthropic.com/news/claude-3-family
87
- codellama-70b-instruct,CodeLlama-70B-instruct,-,-,2024/1,Llama 2 Community,Meta,https://huggingface.co/codellama/CodeLlama-70b-hf
88
- olmo-7b-instruct,OLMo-7B-instruct,-,-,2024/2,Apache-2.0,Allen AI,https://huggingface.co/allenai/OLMo-7B-Instruct
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
leaderboard_table_20240326.csv DELETED
@@ -1,90 +0,0 @@
1
- key,Model,MT-bench (score),MMLU,Knowledge cutoff date,License,Organization,Link
2
- wizardlm-30b,WizardLM-30B,7.01,0.587,2023/6,Non-commercial,Microsoft,https://huggingface.co/WizardLM/WizardLM-30B-V1.0
3
- vicuna-13b-16k,Vicuna-13B-16k,6.92,0.545,2023/7,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-13b-v1.5-16k
4
- wizardlm-13b-v1.1,WizardLM-13B-v1.1,6.76,0.500,2023/7,Non-commercial,Microsoft,https://huggingface.co/WizardLM/WizardLM-13B-V1.1
5
- tulu-30b,Tulu-30B,6.43,0.581,2023/6,Non-commercial,AllenAI/UW,https://huggingface.co/allenai/tulu-30b
6
- guanaco-65b,Guanaco-65B,6.41,0.621,2023/5,Non-commercial,UW,https://huggingface.co/timdettmers/guanaco-65b-merged
7
- openassistant-llama-30b,OpenAssistant-LLaMA-30B,6.41,0.560,2023/4,Non-commercial,OpenAssistant,https://huggingface.co/OpenAssistant/oasst-sft-6-llama-30b-xor
8
- wizardlm-13b-v1.0,WizardLM-13B-v1.0,6.35,0.523,2023/5,Non-commercial,Microsoft,https://huggingface.co/WizardLM/WizardLM-13B-V1.0
9
- vicuna-7b-16k,Vicuna-7B-16k,6.22,0.485,2023/7,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-7b-v1.5-16k
10
- baize-v2-13b,Baize-v2-13B,5.75,0.489,2023/4,Non-commercial,UCSD,https://huggingface.co/project-baize/baize-v2-13b
11
- xgen-7b-8k-inst,XGen-7B-8K-Inst,5.55,0.421,2023/7,Non-commercial,Salesforce,https://huggingface.co/Salesforce/xgen-7b-8k-inst
12
- nous-hermes-13b,Nous-Hermes-13B,5.51,0.493,2023/6,Non-commercial,NousResearch,https://huggingface.co/NousResearch/Nous-Hermes-13b
13
- mpt-30b-instruct,MPT-30B-Instruct,5.22,0.478,2023/6,CC-BY-SA 3.0,MosaicML,https://huggingface.co/mosaicml/mpt-30b-instruct
14
- falcon-40b-instruct,Falcon-40B-Instruct,5.17,0.547,2023/5,Apache 2.0,TII,https://huggingface.co/tiiuae/falcon-40b-instruct
15
- h2o-oasst-openllama-13b,H2O-Oasst-OpenLLaMA-13B,4.63,0.428,2023/6,Apache 2.0,h2oai,https://huggingface.co/h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-13b
16
- gpt-4-1106-preview,GPT-4-1106-preview,9.32,-,2023/4,Proprietary,OpenAI,https://openai.com/blog/new-models-and-developer-products-announced-at-devday
17
- gpt-4-0314,GPT-4-0314,8.96,0.864,2021/9,Proprietary,OpenAI,https://openai.com/research/gpt-4
18
- claude-1,Claude-1,7.90,0.770,-,Proprietary,Anthropic,https://www.anthropic.com/index/introducing-claude
19
- gpt-4-0613,GPT-4-0613,9.18,-,2021/9,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo
20
- claude-2.0,Claude-2.0,8.06,0.785,-,Proprietary,Anthropic,https://www.anthropic.com/index/claude-2
21
- claude-2.1,Claude-2.1,8.18,-,-,Proprietary,Anthropic,https://www.anthropic.com/index/claude-2-1
22
- gpt-3.5-turbo-0613,GPT-3.5-Turbo-0613,8.39,-,2021/9,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-3-5
23
- mixtral-8x7b-instruct-v0.1,Mixtral-8x7b-Instruct-v0.1,8.30,0.706,2023/12,Apache 2.0,Mistral,https://mistral.ai/news/mixtral-of-experts/
24
- claude-instant-1,Claude-Instant-1,7.85,0.734,-,Proprietary,Anthropic,https://www.anthropic.com/index/introducing-claude
25
- gpt-3.5-turbo-0314,GPT-3.5-Turbo-0314,7.94,0.700,2021/9,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-3-5
26
- tulu-2-dpo-70b,Tulu-2-DPO-70B,7.89,-,2023/11,AI2 ImpACT Low-risk,AllenAI/UW,https://huggingface.co/allenai/tulu-2-dpo-70b
27
- yi-34b-chat,Yi-34B-Chat,-,0.735,2023/6,Yi License,01 AI,https://huggingface.co/01-ai/Yi-34B-Chat
28
- gemini-pro,Gemini Pro,-,0.718,2023/4,Proprietary,Google,https://blog.google/technology/ai/gemini-api-developers-cloud/
29
- gemini-pro-dev-api,Gemini Pro (Dev API),-,0.718,2023/4,Proprietary,Google,https://ai.google.dev/docs/gemini_api_overview
30
- bard-jan-24-gemini-pro,Bard (Gemini Pro),-,-,Online,Proprietary,Google,https://bard.google.com/
31
- wizardlm-70b,WizardLM-70B-v1.0,7.71,0.637,2023/8,Llama 2 Community,Microsoft,https://huggingface.co/WizardLM/WizardLM-70B-V1.0
32
- vicuna-33b,Vicuna-33B,7.12,0.592,2023/8,Non-commercial,LMSYS,https://huggingface.co/lmsys/vicuna-33b-v1.3
33
- starling-lm-7b-alpha,Starling-LM-7B-alpha,8.09,0.639,2023/11,CC-BY-NC-4.0,UC Berkeley,https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha
34
- pplx-70b-online,pplx-70b-online,-,-,Online,Proprietary,Perplexity AI,https://blog.perplexity.ai/blog/introducing-pplx-online-llms
35
- openchat-3.5,OpenChat-3.5,7.81,0.643,2023/11,Apache-2.0,OpenChat,https://huggingface.co/openchat/openchat_3.5
36
- openhermes-2.5-mistral-7b,OpenHermes-2.5-Mistral-7b,-,-,2023/11,Apache-2.0,NousResearch,https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B
37
- gpt-3.5-turbo-1106,GPT-3.5-Turbo-1106,8.32,-,2021/9,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-3-5
38
- llama-2-70b-chat,Llama-2-70b-chat,6.86,0.630,2023/7,Llama 2 Community,Meta,https://huggingface.co/meta-llama/Llama-2-70b-chat-hf
39
- solar-10.7b-instruct-v1.0,SOLAR-10.7B-Instruct-v1.0,7.58,0.662,2023/11,CC-BY-NC-4.0,Upstage AI,https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0
40
- dolphin-2.2.1-mistral-7b,Dolphin-2.2.1-Mistral-7B,-,-,2023/10,Apache-2.0,Cognitive Computations,https://huggingface.co/ehartford/dolphin-2.2.1-mistral-7b
41
- wizardlm-13b,WizardLM-13b-v1.2,7.20,0.527,2023/7,Llama 2 Community,Microsoft,https://huggingface.co/WizardLM/WizardLM-13B-V1.2
42
- zephyr-7b-beta,Zephyr-7b-beta,7.34,0.614,2023/10,MIT,HuggingFace,https://huggingface.co/HuggingFaceH4/zephyr-7b-beta
43
- mpt-30b-chat,MPT-30B-chat,6.39,0.504,2023/6,CC-BY-NC-SA-4.0,MosaicML,https://huggingface.co/mosaicml/mpt-30b-chat
44
- vicuna-13b,Vicuna-13B,6.57,0.558,2023/7,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-13b-v1.5
45
- qwen-14b-chat,Qwen-14B-Chat,6.96,0.665,2023/8,Qianwen LICENSE,Alibaba,https://huggingface.co/Qwen/Qwen-14B-Chat
46
- zephyr-7b-alpha,Zephyr-7b-alpha,6.88,-,2023/10,MIT,HuggingFace,https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha
47
- codellama-34b-instruct,CodeLlama-34B-instruct,-,0.537,2023/7,Llama 2 Community,Meta,https://huggingface.co/codellama/CodeLlama-34b-Instruct-hf
48
- falcon-180b-chat,falcon-180b-chat,-,0.680,2023/9,Falcon-180B TII License,TII,https://huggingface.co/tiiuae/falcon-180B-chat
49
- guanaco-33b,Guanaco-33B,6.53,0.576,2023/5,Non-commercial,UW,https://huggingface.co/timdettmers/guanaco-33b-merged
50
- llama-2-13b-chat,Llama-2-13b-chat,6.65,0.536,2023/7,Llama 2 Community,Meta,https://huggingface.co/meta-llama/Llama-2-13b-chat-hf
51
- mistral-7b-instruct,Mistral-7B-Instruct-v0.1,6.84,0.554,2023/9,Apache 2.0,Mistral,https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1
52
- pplx-7b-online,pplx-7b-online,-,-,Online,Proprietary,Perplexity AI,https://blog.perplexity.ai/blog/introducing-pplx-online-llms
53
- llama-2-7b-chat,Llama-2-7b-chat,6.27,0.458,2023/7,Llama 2 Community,Meta,https://huggingface.co/meta-llama/Llama-2-7b-chat-hf
54
- vicuna-7b,Vicuna-7B,6.17,0.498,2023/7,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-7b-v1.5
55
- palm-2,PaLM-Chat-Bison-001,6.40,-,2021/6,Proprietary,Google,https://cloud.google.com/vertex-ai/docs/generative-ai/learn/models#foundation_models
56
- koala-13b,Koala-13B,5.35,0.447,2023/4,Non-commercial,UC Berkeley,https://bair.berkeley.edu/blog/2023/04/03/koala/
57
- chatglm3-6b,ChatGLM3-6B,-,-,2023/10,Apache-2.0,Tsinghua,https://huggingface.co/THUDM/chatglm3-6b
58
- gpt4all-13b-snoozy,GPT4All-13B-Snoozy,5.41,0.430,2023/3,Non-commercial,Nomic AI,https://huggingface.co/nomic-ai/gpt4all-13b-snoozy
59
- mpt-7b-chat,MPT-7B-Chat,5.42,0.320,2023/5,CC-BY-NC-SA-4.0,MosaicML,https://huggingface.co/mosaicml/mpt-7b-chat
60
- chatglm2-6b,ChatGLM2-6B,4.96,0.455,2023/6,Apache-2.0,Tsinghua,https://huggingface.co/THUDM/chatglm2-6b
61
- RWKV-4-Raven-14B,RWKV-4-Raven-14B,3.98,0.256,2023/4,Apache 2.0,RWKV,https://huggingface.co/BlinkDL/rwkv-4-raven
62
- alpaca-13b,Alpaca-13B,4.53,0.481,2023/3,Non-commercial,Stanford,https://crfm.stanford.edu/2023/03/13/alpaca.html
63
- oasst-pythia-12b,OpenAssistant-Pythia-12B,4.32,0.270,2023/4,Apache 2.0,OpenAssistant,https://huggingface.co/OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5
64
- chatglm-6b,ChatGLM-6B,4.50,0.361,2023/3,Non-commercial,Tsinghua,https://huggingface.co/THUDM/chatglm-6b
65
- fastchat-t5-3b,FastChat-T5-3B,3.04,0.477,2023/4,Apache 2.0,LMSYS,https://huggingface.co/lmsys/fastchat-t5-3b-v1.0
66
- stablelm-tuned-alpha-7b,StableLM-Tuned-Alpha-7B,2.75,0.244,2023/4,CC-BY-NC-SA-4.0,Stability AI,https://huggingface.co/stabilityai/stablelm-tuned-alpha-7b
67
- dolly-v2-12b,Dolly-V2-12B,3.28,0.257,2023/4,MIT,Databricks,https://huggingface.co/databricks/dolly-v2-12b
68
- llama-13b,LLaMA-13B,2.61,0.470,2023/2,Non-commercial,Meta,https://arxiv.org/abs/2302.13971
69
- mistral-medium,Mistral Medium,8.61,0.753,-,Proprietary,Mistral,https://mistral.ai/news/la-plateforme/
70
- llama2-70b-steerlm-chat,NV-Llama2-70B-SteerLM-Chat,7.54,0.685,2023/11,Llama 2 Community,Nvidia,https://huggingface.co/nvidia/Llama2-70B-SteerLM-Chat
71
- stripedhyena-nous-7b,StripedHyena-Nous-7B,-,-,2023/12,Apache 2.0,Together AI,https://huggingface.co/togethercomputer/StripedHyena-Nous-7B
72
- deepseek-llm-67b-chat,DeepSeek-LLM-67B-Chat,-,0.713,2023/11,DeepSeek License,DeepSeek AI,https://huggingface.co/deepseek-ai/deepseek-llm-67b-chat
73
- gpt-4-0125-preview,GPT-4-0125-preview,-,-,2023/12,Proprietary,OpenAI,https://openai.com/blog/new-models-and-developer-products-announced-at-devday
74
- qwen1.5-72b-chat,Qwen1.5-72B-Chat,8.61,0.775,2024/2,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen1.5/
75
- qwen1.5-7b-chat,Qwen1.5-7B-Chat,7.6,0.610,2024/2,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen1.5/
76
- qwen1.5-4b-chat,Qwen1.5-4B-Chat,-,0.561,2024/2,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen1.5/
77
- openchat-3.5-0106,OpenChat-3.5-0106,7.8,0.658,2024/1,Apache-2.0,OpenChat,https://huggingface.co/openchat/openchat-3.5-0106
78
- nous-hermes-2-mixtral-8x7b-dpo,Nous-Hermes-2-Mixtral-8x7B-DPO,-,-,2024/1,Apache-2.0,NousResearch,https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO
79
- gpt-3.5-turbo-0125,GPT-3.5-Turbo-0125,-,-,2021/9,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-3-5-turbo
80
- mistral-next,Mistral-Next,-,-,-,Proprietary,Mistral,https://chat.mistral.ai/chat
81
- mistral-large-2402,Mistral-Large-2402,-,0.812,-,Proprietary,Mistral,https://mistral.ai/news/mistral-large/
82
- gemma-7b-it,Gemma-7B-it,-,0.643,2024/2,Gemma license,Google,https://huggingface.co/google/gemma-7b-it
83
- gemma-2b-it,Gemma-2B-it,-,0.423,2024/2,Gemma license,Google,https://huggingface.co/google/gemma-2b-it
84
- mistral-7b-instruct-v0.2,Mistral-7B-Instruct-v0.2,7.6,-,2023/12,Apache-2.0,Mistral,https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2
85
- claude-3-sonnet-20240229,Claude 3 Sonnet,-,0.790,2023/8,Proprietary,Anthropic,https://www.anthropic.com/news/claude-3-family
86
- claude-3-opus-20240229,Claude 3 Opus,-,0.868,2023/8,Proprietary,Anthropic,https://www.anthropic.com/news/claude-3-family
87
- codellama-70b-instruct,CodeLlama-70B-instruct,-,-,2024/1,Llama 2 Community,Meta,https://huggingface.co/codellama/CodeLlama-70b-hf
88
- olmo-7b-instruct,OLMo-7B-instruct,-,-,2024/2,Apache-2.0,Allen AI,https://huggingface.co/allenai/OLMo-7B-Instruct
89
- claude-3-haiku-20240307,Claude 3 Haiku,-,0.752,2023/8,Proprietary,Anthropic,https://www.anthropic.com/news/claude-3-family
90
- starling-lm-7b-beta,Starling-LM-7B-beta,8.12,-,2024/3,Apache-2.0,Nexusflow,https://huggingface.co/Nexusflow/Starling-LM-7B-beta
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
leaderboard_table_20240329.csv DELETED
@@ -1,91 +0,0 @@
1
- key,Model,MT-bench (score),MMLU,Knowledge cutoff date,License,Organization,Link
2
- wizardlm-30b,WizardLM-30B,7.01,0.587,2023/6,Non-commercial,Microsoft,https://huggingface.co/WizardLM/WizardLM-30B-V1.0
3
- vicuna-13b-16k,Vicuna-13B-16k,6.92,0.545,2023/7,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-13b-v1.5-16k
4
- wizardlm-13b-v1.1,WizardLM-13B-v1.1,6.76,0.500,2023/7,Non-commercial,Microsoft,https://huggingface.co/WizardLM/WizardLM-13B-V1.1
5
- tulu-30b,Tulu-30B,6.43,0.581,2023/6,Non-commercial,AllenAI/UW,https://huggingface.co/allenai/tulu-30b
6
- guanaco-65b,Guanaco-65B,6.41,0.621,2023/5,Non-commercial,UW,https://huggingface.co/timdettmers/guanaco-65b-merged
7
- openassistant-llama-30b,OpenAssistant-LLaMA-30B,6.41,0.560,2023/4,Non-commercial,OpenAssistant,https://huggingface.co/OpenAssistant/oasst-sft-6-llama-30b-xor
8
- wizardlm-13b-v1.0,WizardLM-13B-v1.0,6.35,0.523,2023/5,Non-commercial,Microsoft,https://huggingface.co/WizardLM/WizardLM-13B-V1.0
9
- vicuna-7b-16k,Vicuna-7B-16k,6.22,0.485,2023/7,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-7b-v1.5-16k
10
- baize-v2-13b,Baize-v2-13B,5.75,0.489,2023/4,Non-commercial,UCSD,https://huggingface.co/project-baize/baize-v2-13b
11
- xgen-7b-8k-inst,XGen-7B-8K-Inst,5.55,0.421,2023/7,Non-commercial,Salesforce,https://huggingface.co/Salesforce/xgen-7b-8k-inst
12
- nous-hermes-13b,Nous-Hermes-13B,5.51,0.493,2023/6,Non-commercial,NousResearch,https://huggingface.co/NousResearch/Nous-Hermes-13b
13
- mpt-30b-instruct,MPT-30B-Instruct,5.22,0.478,2023/6,CC-BY-SA 3.0,MosaicML,https://huggingface.co/mosaicml/mpt-30b-instruct
14
- falcon-40b-instruct,Falcon-40B-Instruct,5.17,0.547,2023/5,Apache 2.0,TII,https://huggingface.co/tiiuae/falcon-40b-instruct
15
- h2o-oasst-openllama-13b,H2O-Oasst-OpenLLaMA-13B,4.63,0.428,2023/6,Apache 2.0,h2oai,https://huggingface.co/h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-13b
16
- gpt-4-1106-preview,GPT-4-1106-preview,9.32,-,2023/4,Proprietary,OpenAI,https://openai.com/blog/new-models-and-developer-products-announced-at-devday
17
- gpt-4-0314,GPT-4-0314,8.96,0.864,2021/9,Proprietary,OpenAI,https://openai.com/research/gpt-4
18
- claude-1,Claude-1,7.90,0.770,-,Proprietary,Anthropic,https://www.anthropic.com/index/introducing-claude
19
- gpt-4-0613,GPT-4-0613,9.18,-,2021/9,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo
20
- claude-2.0,Claude-2.0,8.06,0.785,-,Proprietary,Anthropic,https://www.anthropic.com/index/claude-2
21
- claude-2.1,Claude-2.1,8.18,-,-,Proprietary,Anthropic,https://www.anthropic.com/index/claude-2-1
22
- gpt-3.5-turbo-0613,GPT-3.5-Turbo-0613,8.39,-,2021/9,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-3-5
23
- mixtral-8x7b-instruct-v0.1,Mixtral-8x7b-Instruct-v0.1,8.30,0.706,2023/12,Apache 2.0,Mistral,https://mistral.ai/news/mixtral-of-experts/
24
- claude-instant-1,Claude-Instant-1,7.85,0.734,-,Proprietary,Anthropic,https://www.anthropic.com/index/introducing-claude
25
- gpt-3.5-turbo-0314,GPT-3.5-Turbo-0314,7.94,0.700,2021/9,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-3-5
26
- tulu-2-dpo-70b,Tulu-2-DPO-70B,7.89,-,2023/11,AI2 ImpACT Low-risk,AllenAI/UW,https://huggingface.co/allenai/tulu-2-dpo-70b
27
- yi-34b-chat,Yi-34B-Chat,-,0.735,2023/6,Yi License,01 AI,https://huggingface.co/01-ai/Yi-34B-Chat
28
- gemini-pro,Gemini Pro,-,0.718,2023/4,Proprietary,Google,https://blog.google/technology/ai/gemini-api-developers-cloud/
29
- gemini-pro-dev-api,Gemini Pro (Dev API),-,0.718,2023/4,Proprietary,Google,https://ai.google.dev/docs/gemini_api_overview
30
- bard-jan-24-gemini-pro,Bard (Gemini Pro),-,-,Online,Proprietary,Google,https://bard.google.com/
31
- wizardlm-70b,WizardLM-70B-v1.0,7.71,0.637,2023/8,Llama 2 Community,Microsoft,https://huggingface.co/WizardLM/WizardLM-70B-V1.0
32
- vicuna-33b,Vicuna-33B,7.12,0.592,2023/8,Non-commercial,LMSYS,https://huggingface.co/lmsys/vicuna-33b-v1.3
33
- starling-lm-7b-alpha,Starling-LM-7B-alpha,8.09,0.639,2023/11,CC-BY-NC-4.0,UC Berkeley,https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha
34
- pplx-70b-online,pplx-70b-online,-,-,Online,Proprietary,Perplexity AI,https://blog.perplexity.ai/blog/introducing-pplx-online-llms
35
- openchat-3.5,OpenChat-3.5,7.81,0.643,2023/11,Apache-2.0,OpenChat,https://huggingface.co/openchat/openchat_3.5
36
- openhermes-2.5-mistral-7b,OpenHermes-2.5-Mistral-7b,-,-,2023/11,Apache-2.0,NousResearch,https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B
37
- gpt-3.5-turbo-1106,GPT-3.5-Turbo-1106,8.32,-,2021/9,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-3-5
38
- llama-2-70b-chat,Llama-2-70b-chat,6.86,0.630,2023/7,Llama 2 Community,Meta,https://huggingface.co/meta-llama/Llama-2-70b-chat-hf
39
- solar-10.7b-instruct-v1.0,SOLAR-10.7B-Instruct-v1.0,7.58,0.662,2023/11,CC-BY-NC-4.0,Upstage AI,https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0
40
- dolphin-2.2.1-mistral-7b,Dolphin-2.2.1-Mistral-7B,-,-,2023/10,Apache-2.0,Cognitive Computations,https://huggingface.co/ehartford/dolphin-2.2.1-mistral-7b
41
- wizardlm-13b,WizardLM-13b-v1.2,7.20,0.527,2023/7,Llama 2 Community,Microsoft,https://huggingface.co/WizardLM/WizardLM-13B-V1.2
42
- zephyr-7b-beta,Zephyr-7b-beta,7.34,0.614,2023/10,MIT,HuggingFace,https://huggingface.co/HuggingFaceH4/zephyr-7b-beta
43
- mpt-30b-chat,MPT-30B-chat,6.39,0.504,2023/6,CC-BY-NC-SA-4.0,MosaicML,https://huggingface.co/mosaicml/mpt-30b-chat
44
- vicuna-13b,Vicuna-13B,6.57,0.558,2023/7,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-13b-v1.5
45
- qwen-14b-chat,Qwen-14B-Chat,6.96,0.665,2023/8,Qianwen LICENSE,Alibaba,https://huggingface.co/Qwen/Qwen-14B-Chat
46
- zephyr-7b-alpha,Zephyr-7b-alpha,6.88,-,2023/10,MIT,HuggingFace,https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha
47
- codellama-34b-instruct,CodeLlama-34B-instruct,-,0.537,2023/7,Llama 2 Community,Meta,https://huggingface.co/codellama/CodeLlama-34b-Instruct-hf
48
- falcon-180b-chat,falcon-180b-chat,-,0.680,2023/9,Falcon-180B TII License,TII,https://huggingface.co/tiiuae/falcon-180B-chat
49
- guanaco-33b,Guanaco-33B,6.53,0.576,2023/5,Non-commercial,UW,https://huggingface.co/timdettmers/guanaco-33b-merged
50
- llama-2-13b-chat,Llama-2-13b-chat,6.65,0.536,2023/7,Llama 2 Community,Meta,https://huggingface.co/meta-llama/Llama-2-13b-chat-hf
51
- mistral-7b-instruct,Mistral-7B-Instruct-v0.1,6.84,0.554,2023/9,Apache 2.0,Mistral,https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1
52
- pplx-7b-online,pplx-7b-online,-,-,Online,Proprietary,Perplexity AI,https://blog.perplexity.ai/blog/introducing-pplx-online-llms
53
- llama-2-7b-chat,Llama-2-7b-chat,6.27,0.458,2023/7,Llama 2 Community,Meta,https://huggingface.co/meta-llama/Llama-2-7b-chat-hf
54
- vicuna-7b,Vicuna-7B,6.17,0.498,2023/7,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-7b-v1.5
55
- palm-2,PaLM-Chat-Bison-001,6.40,-,2021/6,Proprietary,Google,https://cloud.google.com/vertex-ai/docs/generative-ai/learn/models#foundation_models
56
- koala-13b,Koala-13B,5.35,0.447,2023/4,Non-commercial,UC Berkeley,https://bair.berkeley.edu/blog/2023/04/03/koala/
57
- chatglm3-6b,ChatGLM3-6B,-,-,2023/10,Apache-2.0,Tsinghua,https://huggingface.co/THUDM/chatglm3-6b
58
- gpt4all-13b-snoozy,GPT4All-13B-Snoozy,5.41,0.430,2023/3,Non-commercial,Nomic AI,https://huggingface.co/nomic-ai/gpt4all-13b-snoozy
59
- mpt-7b-chat,MPT-7B-Chat,5.42,0.320,2023/5,CC-BY-NC-SA-4.0,MosaicML,https://huggingface.co/mosaicml/mpt-7b-chat
60
- chatglm2-6b,ChatGLM2-6B,4.96,0.455,2023/6,Apache-2.0,Tsinghua,https://huggingface.co/THUDM/chatglm2-6b
61
- RWKV-4-Raven-14B,RWKV-4-Raven-14B,3.98,0.256,2023/4,Apache 2.0,RWKV,https://huggingface.co/BlinkDL/rwkv-4-raven
62
- alpaca-13b,Alpaca-13B,4.53,0.481,2023/3,Non-commercial,Stanford,https://crfm.stanford.edu/2023/03/13/alpaca.html
63
- oasst-pythia-12b,OpenAssistant-Pythia-12B,4.32,0.270,2023/4,Apache 2.0,OpenAssistant,https://huggingface.co/OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5
64
- chatglm-6b,ChatGLM-6B,4.50,0.361,2023/3,Non-commercial,Tsinghua,https://huggingface.co/THUDM/chatglm-6b
65
- fastchat-t5-3b,FastChat-T5-3B,3.04,0.477,2023/4,Apache 2.0,LMSYS,https://huggingface.co/lmsys/fastchat-t5-3b-v1.0
66
- stablelm-tuned-alpha-7b,StableLM-Tuned-Alpha-7B,2.75,0.244,2023/4,CC-BY-NC-SA-4.0,Stability AI,https://huggingface.co/stabilityai/stablelm-tuned-alpha-7b
67
- dolly-v2-12b,Dolly-V2-12B,3.28,0.257,2023/4,MIT,Databricks,https://huggingface.co/databricks/dolly-v2-12b
68
- llama-13b,LLaMA-13B,2.61,0.470,2023/2,Non-commercial,Meta,https://arxiv.org/abs/2302.13971
69
- mistral-medium,Mistral Medium,8.61,0.753,-,Proprietary,Mistral,https://mistral.ai/news/la-plateforme/
70
- llama2-70b-steerlm-chat,NV-Llama2-70B-SteerLM-Chat,7.54,0.685,2023/11,Llama 2 Community,Nvidia,https://huggingface.co/nvidia/Llama2-70B-SteerLM-Chat
71
- stripedhyena-nous-7b,StripedHyena-Nous-7B,-,-,2023/12,Apache 2.0,Together AI,https://huggingface.co/togethercomputer/StripedHyena-Nous-7B
72
- deepseek-llm-67b-chat,DeepSeek-LLM-67B-Chat,-,0.713,2023/11,DeepSeek License,DeepSeek AI,https://huggingface.co/deepseek-ai/deepseek-llm-67b-chat
73
- gpt-4-0125-preview,GPT-4-0125-preview,-,-,2023/12,Proprietary,OpenAI,https://openai.com/blog/new-models-and-developer-products-announced-at-devday
74
- qwen1.5-72b-chat,Qwen1.5-72B-Chat,8.61,0.775,2024/2,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen1.5/
75
- qwen1.5-7b-chat,Qwen1.5-7B-Chat,7.6,0.610,2024/2,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen1.5/
76
- qwen1.5-4b-chat,Qwen1.5-4B-Chat,-,0.561,2024/2,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen1.5/
77
- openchat-3.5-0106,OpenChat-3.5-0106,7.8,0.658,2024/1,Apache-2.0,OpenChat,https://huggingface.co/openchat/openchat-3.5-0106
78
- nous-hermes-2-mixtral-8x7b-dpo,Nous-Hermes-2-Mixtral-8x7B-DPO,-,-,2024/1,Apache-2.0,NousResearch,https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO
79
- gpt-3.5-turbo-0125,GPT-3.5-Turbo-0125,-,-,2021/9,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-3-5-turbo
80
- mistral-next,Mistral-Next,-,-,-,Proprietary,Mistral,https://chat.mistral.ai/chat
81
- mistral-large-2402,Mistral-Large-2402,-,0.812,-,Proprietary,Mistral,https://mistral.ai/news/mistral-large/
82
- gemma-7b-it,Gemma-7B-it,-,0.643,2024/2,Gemma license,Google,https://huggingface.co/google/gemma-7b-it
83
- gemma-2b-it,Gemma-2B-it,-,0.423,2024/2,Gemma license,Google,https://huggingface.co/google/gemma-2b-it
84
- mistral-7b-instruct-v0.2,Mistral-7B-Instruct-v0.2,7.6,-,2023/12,Apache-2.0,Mistral,https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2
85
- claude-3-sonnet-20240229,Claude 3 Sonnet,-,0.790,2023/8,Proprietary,Anthropic,https://www.anthropic.com/news/claude-3-family
86
- claude-3-opus-20240229,Claude 3 Opus,-,0.868,2023/8,Proprietary,Anthropic,https://www.anthropic.com/news/claude-3-family
87
- codellama-70b-instruct,CodeLlama-70B-instruct,-,-,2024/1,Llama 2 Community,Meta,https://huggingface.co/codellama/CodeLlama-70b-hf
88
- olmo-7b-instruct,OLMo-7B-instruct,-,-,2024/2,Apache-2.0,Allen AI,https://huggingface.co/allenai/OLMo-7B-Instruct
89
- claude-3-haiku-20240307,Claude 3 Haiku,-,0.752,2023/8,Proprietary,Anthropic,https://www.anthropic.com/news/claude-3-family
90
- starling-lm-7b-beta,Starling-LM-7B-beta,8.12,-,2024/3,Apache-2.0,Nexusflow,https://huggingface.co/Nexusflow/Starling-LM-7B-beta
91
- command-r,Command R,-,-,2024/3,CC-BY-NC-4.0,Cohere,https://txt.cohere.com/command-r