Spaces:
Runtime error
Runtime error
Upload 2 files
Browse files- elo_results_20231002.pkl +2 -2
- leaderboard_table_20231002.csv +11 -10
elo_results_20231002.pkl
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5b3ed8668fd1321e28623fc434269274a70ed011b67513cb3ce785d3309f458
|
3 |
+
size 38147
|
leaderboard_table_20231002.csv
CHANGED
@@ -17,27 +17,28 @@ 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,
|
21 |
-
WizardLM-70b-v1.0,7.71,
|
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,
|
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,
|
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 |
Llama-2-13b-chat,6.65,1012,0.536,Llama 2 Community,https://huggingface.co/meta-llama/Llama-2-13b-chat-hf
|
30 |
-
PaLM-Chat-Bison-001,6.40,
|
31 |
Vicuna-7B,6.17,997,0.498,Llama 2 Community,https://huggingface.co/lmsys/vicuna-7b-v1.5
|
32 |
Llama-2-7b-chat,6.27,985,0.458,Llama 2 Community,https://huggingface.co/meta-llama/Llama-2-7b-chat-hf
|
33 |
-
Koala-13B,5.35,
|
34 |
-
GPT4All-13B-Snoozy,5.41,
|
35 |
ChatGLM2-6B,4.96,945,0.455,Apache-2.0,https://huggingface.co/THUDM/chatglm2-6b
|
36 |
-
MPT-7B-Chat,5.42,
|
37 |
RWKV-4-Raven-14B,3.98,933,0.256,Apache 2.0,https://huggingface.co/BlinkDL/rwkv-4-raven
|
38 |
Alpaca-13B,4.53,914,0.481,Non-commercial,https://crfm.stanford.edu/2023/03/13/alpaca.html
|
39 |
-
OpenAssistant-Pythia-12B,4.32,
|
40 |
-
ChatGLM-6B,4.50,
|
41 |
FastChat-T5-3B,3.04,884,0.477,Apache 2.0,https://huggingface.co/lmsys/fastchat-t5-3b-v1.0
|
42 |
StableLM-Tuned-Alpha-7B,2.75,853,0.244,CC-BY-NC-SA-4.0,https://huggingface.co/stabilityai/stablelm-tuned-alpha-7b
|
43 |
Dolly-V2-12B,3.28,832,0.257,MIT,https://huggingface.co/databricks/dolly-v2-12b
|
|
|
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
|