Hugging Face's logo

Spaces:
lmarena-ai
/
chatbot-arena-leaderboard
Running

App Files Community
61

Merge arena hard leaderboard and leaderboard table csv file

#46
by connorchenn - opened
base: refs/heads/main
←
from: refs/pr/46
Discussion Files changed
+5
-8434
This view is limited to 50 files because it contains too many changes.  See the raw diff here.
Files changed (50) hide show
  1. README.md +2 -3
  2. app.py +1 -6
  3. arena_hard_auto_leaderboard_v0.1.csv +0 -61
  4. elo_results_20240722.pkl +0 -3
  5. elo_results_20240725.pkl +0 -3
  6. elo_results_20240730.pkl +0 -3
  7. elo_results_20240731.pkl +0 -3
  8. elo_results_20240801.pkl +0 -3
  9. elo_results_20240805.pkl +0 -3
  10. elo_results_20240806.pkl +0 -3
  11. elo_results_20240813.pkl +0 -3
  12. elo_results_20240822.pkl +0 -3
  13. elo_results_20240823.pkl +0 -3
  14. elo_results_20240827.pkl +0 -3
  15. elo_results_20240828.pkl +0 -3
  16. elo_results_20240904.pkl +0 -3
  17. elo_results_20240915.pkl +0 -3
  18. elo_results_20240917.pkl +0 -3
  19. elo_results_20240927.pkl +0 -3
  20. elo_results_20241007.pkl +0 -3
  21. elo_results_20241015.pkl +0 -3
  22. elo_results_20241023.pkl +0 -3
  23. elo_results_20241028.pkl +0 -3
  24. elo_results_20241104.pkl +0 -3
  25. elo_results_20241112.pkl +0 -3
  26. elo_results_20241113.pkl +0 -3
  27. elo_results_20241120.pkl +0 -3
  28. elo_results_20241121.pkl +0 -3
  29. elo_results_20241122.pkl +0 -3
  30. elo_results_20241201.pkl +0 -3
  31. elo_results_20241205.pkl +0 -3
  32. elo_results_20241210.pkl +0 -3
  33. elo_results_20241215.pkl +0 -3
  34. elo_results_20241218.pkl +0 -3
  35. elo_results_20241222.pkl +0 -3
  36. elo_results_20241230.pkl +0 -3
  37. elo_results_20250105.pkl +0 -3
  38. elo_results_20250115.pkl +0 -3
  39. elo_results_20250119.pkl +0 -3
  40. elo_results_20250121.pkl +0 -3
  41. elo_results_20250122.pkl +0 -3
  42. elo_results_20250124.pkl +0 -3
  43. elo_results_20250128.pkl +0 -3
  44. elo_results_20250203.pkl +0 -3
  45. elo_results_20250205.pkl +0 -3
  46. leaderboard_table_20240722.csv +0 -135
  47. leaderboard_table_20240725.csv +0 -136
  48. leaderboard_table_20240730.csv +0 -140
  49. leaderboard_table_20240731.csv +0 -144
  50. leaderboard_table_20240801.csv +0 -145
README.md CHANGED
@@ -1,5 +1,5 @@
1
  ---
2
- title: Chatbot Arena Leaderboard
3
  emoji: 🏆🤖
4
  colorFrom: indigo
5
  colorTo: green
@@ -7,8 +7,7 @@ sdk: gradio
7
  pinned: false
8
  license: apache-2.0
9
  tags:
10
- - leaderboard
11
- sdk_version: 4.44.1
12
  ---
13
 
14
  Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
1
  ---
2
+ title: LMSys Chatbot Arena Leaderboard
3
  emoji: 🏆🤖
4
  colorFrom: indigo
5
  colorTo: green
 
7
  pinned: false
8
  license: apache-2.0
9
  tags:
10
+ - leaderboard
 
11
  ---
12
 
13
  Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
app.py CHANGED
@@ -6,7 +6,6 @@ import glob
6
  import re
7
  import gradio as gr
8
 
9
-
10
  def load_demo(url_params, request: gr.Request):
11
  logger.info(f"load_demo. ip: {request.client.host}. params: {url_params}")
12
  return basic_component_values + leader_component_values
@@ -42,7 +41,7 @@ def build_demo(elo_results_file, leaderboard_table_file):
42
  css=block_css,
43
  ) as demo:
44
  leader_components = build_leaderboard_tab(
45
- elo_results_file, leaderboard_table_file, arena_hard_file, show_plot=True, mirror=True
46
  )
47
  return demo
48
 
@@ -63,10 +62,6 @@ if __name__ == "__main__":
63
  leaderboard_table_files = glob.glob("leaderboard_table_*.csv")
64
  leaderboard_table_files.sort(key=lambda x: int(x[18:-4]))
65
  leaderboard_table_file = leaderboard_table_files[-1]
66
-
67
- arena_hard_files = glob.glob("arena_hard_auto_leaderboard_*.csv")
68
- arena_hard_files.sort(key=lambda x: float(x[29:32]))
69
- arena_hard_file = arena_hard_files[-1]
70
 
71
  demo = build_demo(elo_result_file, leaderboard_table_file)
72
  demo.launch(share=args.share, server_name=args.host, server_port=args.port)
 
6
  import re
7
  import gradio as gr
8
 
 
9
  def load_demo(url_params, request: gr.Request):
10
  logger.info(f"load_demo. ip: {request.client.host}. params: {url_params}")
11
  return basic_component_values + leader_component_values
 
41
  css=block_css,
42
  ) as demo:
43
  leader_components = build_leaderboard_tab(
44
+ elo_results_file, leaderboard_table_file, show_plot=True, mirror=True
45
  )
46
  return demo
47
 
 
62
  leaderboard_table_files = glob.glob("leaderboard_table_*.csv")
63
  leaderboard_table_files.sort(key=lambda x: int(x[18:-4]))
64
  leaderboard_table_file = leaderboard_table_files[-1]
 
 
 
 
65
 
66
  demo = build_demo(elo_result_file, leaderboard_table_file)
67
  demo.launch(share=args.share, server_name=args.host, server_port=args.port)
arena_hard_auto_leaderboard_v0.1.csv DELETED
@@ -1,61 +0,0 @@
1
- model,score,rating_q025,rating_q975,CI,avg_tokens,date
2
- gpt-4-turbo-2024-04-09,82.63,80.75,84.6,"(1.9, 2.0)",662.0,2024-07-31
3
- claude-3-5-sonnet-20240620,79.35,77.25,80.62,"(2.1, 1.3)",567.0,2024-07-31
4
- gpt-4o-2024-05-13,79.21,77.42,80.71,"(1.8, 1.5)",696.0,2024-07-31
5
- gpt-4-0125-preview,77.96,75.94,79.9,"(2.0, 1.9)",619.0,2024-07-31
6
- athene-70b-0725,76.83,74.84,78.74,"(2.0, 1.9)",683.0,2024-07-31
7
- gpt-4o-mini-2024-07-18,74.94,72.66,77.07,"(2.3, 2.1)",668.0,2024-07-31
8
- gemini-1.5-pro-api-0514,71.96,69.62,74.62,"(2.3, 2.7)",676.0,2024-07-31
9
- yi-large-preview,71.48,69.02,73.37,"(2.5, 1.9)",720.0,2024-07-31
10
- mistral-large-2407,70.42,68.11,72.43,"(2.3, 2.0)",623.0,2024-07-31
11
- llama-3.1-405b-instruct,64.09,61.43,66.55,"(2.7, 2.5)",633.0,2024-07-31
12
- glm-4-0520,63.84,61.28,66.19,"(2.6, 2.3)",636.0,2024-07-31
13
- yi-large,63.7,61.76,65.86,"(1.9, 2.2)",626.0,2024-07-31
14
- deepseek-coder-v2,62.3,59.82,64.72,"(2.5, 2.4)",578.0,2024-07-31
15
- claude-3-opus-20240229,60.36,57.56,62.34,"(2.8, 2.0)",541.0,2024-07-31
16
- gemma-2-27b-it,57.51,55.11,60.12,"(2.4, 2.6)",577.0,2024-07-31
17
- llama-3.1-70b-instruct,55.73,52.85,58.2,"(2.9, 2.5)",628.0,2024-07-31
18
- glm-4-0116,55.72,53.83,58.16,"(1.9, 2.4)",622.0,2024-07-31
19
- gemini-1.5-pro-api-0409-preview,53.37,51.13,56.66,"(2.2, 3.3)",478.0,2024-07-31
20
- glm-4-air,50.88,48.62,53.21,"(2.3, 2.3)",619.0,2024-07-31
21
- gpt-4-0314,50.0,50.0,50.0,"(0.0, 0.0)",423.0,2024-07-31
22
- gemini-1.5-flash-api-0514,49.61,47.46,52.17,"(2.1, 2.6)",642.0,2024-07-31
23
- qwen2-72b-instruct,46.86,44.57,49.29,"(2.3, 2.4)",515.0,2024-07-31
24
- claude-3-sonnet-20240229,46.8,44.12,49.04,"(2.7, 2.2)",552.0,2024-07-31
25
- llama-3-70b-instruct,46.57,43.84,49.18,"(2.7, 2.6)",591.0,2024-07-31
26
- claude-3-haiku-20240307,41.47,39.57,44.02,"(1.9, 2.6)",505.0,2024-07-31
27
- gpt-4-0613,37.9,35.6,40.36,"(2.3, 2.5)",354.0,2024-07-31
28
- mistral-large-2402,37.71,34.81,39.77,"(2.9, 2.1)",400.0,2024-07-31
29
- mixtral-8x22b-instruct-v0.1,36.36,34.21,38.55,"(2.1, 2.2)",430.0,2024-07-31
30
- qwen1.5-72b-chat,36.12,33.88,38.15,"(2.2, 2.0)",474.0,2024-07-31
31
- phi-3-medium-4k-instruct,33.37,31.26,35.14,"(2.1, 1.8)",517.0,2024-07-31
32
- command-r-plus,33.07,30.85,35.12,"(2.2, 2.0)",541.0,2024-07-31
33
- mistral-medium,31.9,29.66,34.31,"(2.2, 2.4)",485.0,2024-07-31
34
- phi-3-small-8k-instruct,29.77,27.94,31.97,"(1.8, 2.2)",568.0,2024-07-31
35
- mistral-next,27.37,25.4,29.09,"(2.0, 1.7)",297.0,2024-07-31
36
- gpt-3.5-turbo-0613,24.82,22.54,26.29,"(2.3, 1.5)",401.0,2024-07-31
37
- dbrx-instruct-preview,24.63,22.33,26.83,"(2.3, 2.2)",415.0,2024-07-31
38
- claude-2.0,23.99,21.71,25.65,"(2.3, 1.7)",295.0,2024-07-31
39
- mixtral-8x7b-instruct-v0.1,23.4,21.38,25.41,"(2.0, 2.0)",457.0,2024-07-31
40
- gpt-3.5-turbo-0125,23.34,21.67,25.27,"(1.7, 1.9)",329.0,2024-07-31
41
- yi-34b-chat,23.15,20.75,24.7,"(2.4, 1.6)",611.0,2024-07-31
42
- starling-lm-7b-beta,23.01,20.81,24.66,"(2.2, 1.6)",530.0,2024-07-31
43
- claude-2.1,22.77,20.65,25.43,"(2.1, 2.7)",290.0,2024-07-31
44
- llama-3.1-8b-instruct,21.34,19.71,23.09,"(1.6, 1.8)",861.0,2024-07-31
45
- snorkel-mistral-pairrm-dpo,20.73,19.04,22.05,"(1.7, 1.3)",564.0,2024-07-31
46
- llama-3-8b-instruct,20.56,18.82,22.61,"(1.7, 2.1)",585.0,2024-07-31
47
- gpt-3.5-turbo-1106,18.87,17.06,20.58,"(1.8, 1.7)",285.0,2024-07-31
48
- gpt-3.5-turbo-0314,18.05,16.57,20.06,"(1.5, 2.0)",334.0,2024-07-31
49
- gemini-pro,17.8,15.96,19.32,"(1.8, 1.5)",322.0,2024-07-31
50
- snowflake-arctic-instruct,17.61,16.12,19.27,"(1.5, 1.7)",365.0,2024-07-31
51
- command-r,17.02,15.73,18.51,"(1.3, 1.5)",432.0,2024-07-31
52
- phi-3-mini-128k-instruct,15.43,13.94,17.02,"(1.5, 1.6)",609.0,2024-07-31
53
- tulu-2-dpo-70b,14.99,13.05,16.82,"(1.9, 1.8)",550.0,2024-07-31
54
- starling-lm-7b-alpha,12.8,11.23,14.5,"(1.6, 1.7)",483.0,2024-07-31
55
- mistral-7b-instruct,12.57,11.05,14.11,"(1.5, 1.5)",541.0,2024-07-31
56
- gemma-1.1-7b-it,12.09,10.61,13.43,"(1.5, 1.3)",341.0,2024-07-31
57
- llama-2-70b-chat,11.55,10.02,13.01,"(1.5, 1.5)",595.0,2024-07-31
58
- vicuna-33b,8.63,7.59,9.84,"(1.0, 1.2)",451.0,2024-07-31
59
- gemma-7b-it,7.47,6.5,8.6,"(1.0, 1.1)",378.0,2024-07-31
60
- gemma-1.1-2b-it,3.37,2.74,4.14,"(0.6, 0.8)",316.0,2024-07-31
61
- gemma-2b-it,3.0,2.33,3.67,"(0.7, 0.7)",369.0,2024-07-31
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
elo_results_20240722.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c01b5a786ffd8bf64b72d39ca3fc7dee5483852c6a515f515532c8096a6e16d4
3
- size 3054518
 
 
 
 
elo_results_20240725.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1bfde449e424f12c9316f0c64062fc1ef9926e4a924bbaeafa455fcde0decb6f
3
- size 3073542
 
 
 
 
elo_results_20240730.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8db59f5f0852f26600f85c3188547e5d97b4641906c979bcc178cd5be7a7554c
3
- size 3137995
 
 
 
 
elo_results_20240731.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9aaff49a611fef8ff7bec058827d7de3426973c15bc538ac6bb39e764cc14b34
3
- size 3157482
 
 
 
 
elo_results_20240801.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:cdaa16f762adc54cbe05ab03dff88587491193852846b749980294b7f1ea2bec
3
- size 3182414
 
 
 
 
elo_results_20240805.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e638bfe870e4409c4d768d57287cc8f6310caf85191d8020ba89f7f59ee9f6d8
3
- size 3202114
 
 
 
 
elo_results_20240806.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a4f31f36636a280589bb1039f9d1f405a989df6a8f74d1af30555d891b23a416
3
- size 3261205
 
 
 
 
elo_results_20240813.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4c5dfd4247b704f07e61ae27dc0642a3d3cfa9a6872cc3dc03d1888a594de9f
3
- size 2943734
 
 
 
 
elo_results_20240822.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c733894de1252232a63ce3632abe52504fb6bcf43e17bb49fea2b5ad8d76116f
3
- size 3004697
 
 
 
 
elo_results_20240823.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec103aa6bf5d0f02f8bd2c69c8ccfc8f1be1b44c7dc004d967c8d5ce470975b5
3
- size 3039588
 
 
 
 
elo_results_20240827.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:fbcf63bc492b9e2018fdd2c82924f375f12db20dd577f2c139a8ff82a2d08159
3
- size 3093445
 
 
 
 
elo_results_20240828.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b7da13b5f061a7a5a112e5ca45ff707d6cf6259c8a01b40ea5b77bbd5bd3d5b0
3
- size 3819732
 
 
 
 
elo_results_20240904.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf6117b1e28bb982e965d20b927685dce98750a82c255b868588b5b2318aaee9
3
- size 3486555
 
 
 
 
elo_results_20240915.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:42512fe148c81eeab05961ed64fe446dc7f6ed3703f976fc4c8c2a6a3a3e6bef
3
- size 3726145
 
 
 
 
elo_results_20240917.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d15ed36a6e429a9213e9230fbd28de05e7788f758c4282660dd77a4689f98590
3
- size 3768775
 
 
 
 
elo_results_20240927.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c96f9a95fbbf44b8cb46129cc8ea09eef1bb6e43b8ec12d1c8837091d23ee69
3
- size 3860967
 
 
 
 
elo_results_20241007.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3891408ad17e52226989783562eb75f784dfb1d0a30dd9051e943b48cd0b117c
3
- size 3919717
 
 
 
 
elo_results_20241015.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6daea1d6b24298f32f23c903872aa6c852453de29bf82aa0d2e7aaf5337af715
3
- size 4058396
 
 
 
 
elo_results_20241023.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e592a6807b4affbc2e203b385ff491743116b4854c9bcd3c3bbf037fba6092f
3
- size 4374135
 
 
 
 
elo_results_20241028.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb1b06bd57f44c46862bb7c326c39e09fa0e298257d3e8fb96d466a7200fc77d
3
- size 4417082
 
 
 
 
elo_results_20241104.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c0129cb6833f0d81f9407489883c588f5712666ecdc35111de725d3502e61a07
3
- size 4472516
 
 
 
 
elo_results_20241112.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab321a67e6831f495d8ac7d6e052f16eae495fb4a82454f8d7bd361bda6f4706
3
- size 4472047
 
 
 
 
elo_results_20241113.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d0493678e9a9d2d86bdc8adf483824ef731b8efe8a41c5cef1d81bf21f5e7e9
3
- size 4496349
 
 
 
 
elo_results_20241120.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e5f7d30d02d57f07d0506d385d2007fb7ae4a33a24a2e8e62fc95e9434c565e
3
- size 4585156
 
 
 
 
elo_results_20241121.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:610c77a4c4b47f1bb256a3dfa1808d5d32b5d9c819aa5f34b1aae857a959c303
3
- size 4613615
 
 
 
 
elo_results_20241122.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5387ed94e44688ff4cacc52644290409dd09580a0c745016c5d473ff9f3368bd
3
- size 4656304
 
 
 
 
elo_results_20241201.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e43a1652cfd47ab95459d2a9ac8e5fc8065001f8160dcc8c460c4b1bbda2e58e
3
- size 4743052
 
 
 
 
elo_results_20241205.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:651b61a2fdb0f16884975c2d71577f67e311ed0b5675badbe5db2f4b0068d3e5
3
- size 4757570
 
 
 
 
elo_results_20241210.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ebcf524b476eba3cc260d9e3f8f8e42d187c56481748645276cd70ea6e1caaa2
3
- size 4796359
 
 
 
 
elo_results_20241215.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:af899ac7ceed98b9c127c69fad5b6115bd02e00fe94a2a580734639ef9cdb417
3
- size 4928341
 
 
 
 
elo_results_20241218.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9380779e9effeef27f1face0759c2e11075c8b2c4a809f565a9cfd40944bb7a2
3
- size 4956709
 
 
 
 
elo_results_20241222.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:030bc6db11694fcf5e025e6aa849d28e61dc4c7bcb66a0b562f7cd2673d9599d
3
- size 5018497
 
 
 
 
elo_results_20241230.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:517d699389bdbf7f01ec341306be72ffad2ee36d224a240369f817ae0486db87
3
- size 5051817
 
 
 
 
elo_results_20250105.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:609f7b97d9c67d79214c8083a3d8f24f6e0893c3fd45cb079eb2748b7acbc5e8
3
- size 5979482
 
 
 
 
elo_results_20250115.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:758c111032a6e355760d5d4074b435174100d43faf1d96ca07e34b76477c56a3
3
- size 6054581
 
 
 
 
elo_results_20250119.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:27105cd16c8d3456548c8ab8e93d52abc71634b1e70237173b260cb0bbab93df
3
- size 6082897
 
 
 
 
elo_results_20250121.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:81bfdd73af127cf20a9c5effd9871d7d5c5b1dd2ce1e9c2c5076b45feff844df
3
- size 6111217
 
 
 
 
elo_results_20250122.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9e220831e892b7f69e6ac0f4d21c3b091aaf59b0b51c7a19e5618980b07068a
3
- size 6115326
 
 
 
 
elo_results_20250124.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b3ea59502af8135c8cd24074d6a1ff5f710553ab46acaab9259a6bbeed535851
3
- size 6234818
 
 
 
 
elo_results_20250128.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:bdbd9f8bacb67e3e4e829e077b5621fb443f50b6ce0f73ab017607ffccccce1a
3
- size 6172158
 
 
 
 
elo_results_20250203.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c591519e3818519bace906c2a79aa9cba7cb09ee5074a7f389def5ff84c1b6aa
3
- size 6221605
 
 
 
 
elo_results_20250205.pkl DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:53603d4d811e02261964a97bc8cbb46be4380f914388667974ba483e94262e3e
3
- size 6305480
 
 
 
 
leaderboard_table_20240722.csv DELETED
@@ -1,135 +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
92
- qwen1.5-14b-chat,Qwen1.5-14B-Chat,7.91,0.676,2024/2,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen1.5/
93
- qwen1.5-32b-chat,Qwen1.5-32B-Chat,8.30,0.734,2024/2,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen1.5-32b/
94
- command-r-plus,Command R+,-,-,2024/3,CC-BY-NC-4.0,Cohere,https://txt.cohere.com/command-r-plus-microsoft-azure/
95
- gemma-1.1-7b-it,Gemma-1.1-7B-it,-,0.643,2024/2,Gemma license,Google,https://huggingface.co/google/gemma-1.1-7b-it
96
- dbrx-instruct-preview,DBRX-Instruct-Preview,-,0.737,2023/12,DBRX LICENSE,Databricks,https://www.databricks.com/blog/introducing-dbrx-new-state-art-open-llm
97
- gpt-4-turbo-2024-04-09,GPT-4-Turbo-2024-04-09,-,-,2023/12,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4
98
- gemma-1.1-2b-it,Gemma-1.1-2B-it,-,0.643,2024/2,Gemma license,Google,https://huggingface.co/google/gemma-1.1-2b-it
99
- reka-flash-21b-20240226,Reka-Flash-21B,-,0.735,2023/11,Proprietary,Reka AI,https://www.reka.ai/news/reka-flash-efficient-and-capable-multimodal-language-models
100
- reka-flash-21b-20240226-online,Reka-Flash-21B-online,-,-,Online,Proprietary,Reka AI,https://docs.reka.ai/http-api.html#generation
101
- zephyr-orpo-141b-A35b-v0.1,Zephyr-ORPO-141b-A35b-v0.1,-,-,2024/4,Apache 2.0,HuggingFace,https://huggingface.co/HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1
102
- mixtral-8x22b-instruct-v0.1,Mixtral-8x22b-Instruct-v0.1,-,0.778,2024/4,Apache 2.0,Mistral,https://mistral.ai/news/mixtral-8x22b/
103
- llama-3-70b-instruct,Llama-3-70b-Instruct,-,0.820,2023/12,Llama 3 Community,Meta,https://llama.meta.com/llama3/
104
- llama-3-8b-instruct,Llama-3-8b-Instruct,-,0.684,2023/3,Llama 3 Community,Meta,https://llama.meta.com/llama3/
105
- gemini-1.5-pro-api-0409-preview,Gemini-1.5-Pro-API-0409-Preview,-,0.819,2023/11,Proprietary,Google,https://blog.google/technology/ai/google-gemini-next-generation-model-february-2024/
106
- phi-3-mini-128k-instruct,Phi-3-Mini-128k-Instruct,-,0.681,2023/10,MIT,Microsoft,https://azure.microsoft.com/en-us/blog/introducing-phi-3-redefining-whats-possible-with-slms/
107
- snowflake-arctic-instruct,Snowflake Arctic Instruct,-,0.673,2024/4,Apache 2.0,Snowflake,https://www.snowflake.com/blog/arctic-open-efficient-foundation-language-models-snowflake/
108
- qwen-max-0428,Qwen-Max-0428,-,-,-,Proprietary,Alibaba,https://help.aliyun.com/zh/dashscope/developer-reference/api-details
109
- qwen1.5-110b-chat,Qwen1.5-110B-Chat,8.88,0.804,2024/4,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen1.5-110b/
110
- reka-core-20240501,Reka-Core-20240501,-,0.832,-,Proprietary,Reka AI,https://www.reka.ai/news/reka-core-our-frontier-class-multimodal-language-model
111
- gpt-4o-2024-05-13,GPT-4o-2024-05-13,-,0.887,2023/10,Proprietary,OpenAI,https://openai.com/index/hello-gpt-4o/
112
- phi-3-mini-4k-instruct,Phi-3-Mini-4k-Instruct,-,0.688,2023/10,MIT,Microsoft,https://huggingface.co/microsoft/Phi-3-mini-4k-instruct
113
- yi-large-preview,Yi-Large-preview,-,-,Unknown,Proprietary,01 AI,https://platform.lingyiwanwu.com/docs#%E6%A8%A1%E5%9E%8B
114
- glm-4-0116,GLM-4-0116,-,-,Unknown,Proprietary,Zhipu AI,https://open.bigmodel.cn/
115
- gemini-advanced-0514,Gemini-Advanced-0514,-,-,Online,Proprietary,Google,https://gemini.google.com/advanced
116
- gemini-1.5-pro-api-0514,Gemini-1.5-Pro-API-0514,-,0.859,2023/11,Proprietary,Google,https://deepmind.google/technologies/gemini/pro
117
- gemini-1.5-flash-api-0514,Gemini-1.5-Flash-API-0514,-,0.789,2023/11,Proprietary,Google,https://deepmind.google/technologies/gemini/flash/
118
- yi-34b-chat,Yi-34B-Chat,-,0.735,2023/6,Yi License,01 AI,https://huggingface.co/01-ai/Yi-34B-Chat
119
- yi-1.5-34b-chat,Yi-1.5-34B-Chat,-,0.768,2024/5,Apache-2.0,01 AI,https://huggingface.co/01-ai/Yi-1.5-34B-Chat
120
- phi-3-small-8k-instruct,Phi-3-Small-8k-Instruct,-,0.757,2023/10,MIT,Microsoft,https://huggingface.co/microsoft/Phi-3-small-8k-instruct
121
- phi-3-medium-4k-instruct,Phi-3-Medium-4k-Instruct,-,0.780,2023/10,MIT,Microsoft,https://huggingface.co/microsoft/Phi-3-medium-4k-instruct
122
- qwen2-72b-instruct,Qwen2-72B-Instruct,9.12,0.842,2024/6,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen2/
123
- yi-large,Yi-Large,-,-,Unknown,Proprietary,01 AI,https://platform.01.ai/docs#models-and-pricing
124
- nemotron-4-340b-instruct,Nemotron-4-340B-Instruct,-,-,2023/6,NVIDIA Open Model,Nvidia,https://huggingface.co/nvidia/Nemotron-4-340B-Instruct
125
- reka-flash-preview-20240611,Reka-Flash-Preview-20240611,-,-,-,Proprietary,Reka AI,https://docs.reka.ai/http-api.html#generation
126
- glm-4-0520,GLM-4-0520,-,-,Unknown,Proprietary,Zhipu AI,https://open.bigmodel.cn/dev/api#language
127
- deepseek-coder-v2,DeepSeek-Coder-V2-Instruct,-,-,2024/6,DeepSeek License,DeepSeek AI,https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Instruct
128
- claude-3-5-sonnet-20240620,Claude 3.5 Sonnet,-,0.887,2024/4,Proprietary,Anthropic,https://www.anthropic.com/news/claude-3-5-sonnet
129
- gemma-2-27b-it,Gemma-2-27B-it,-,-,2024/6,Gemma license,Google,https://ai.google.dev/gemma
130
- gemma-2-9b-it,Gemma-2-9B-it,-,-,2024/6,Gemma license,Google,https://ai.google.dev/gemma
131
- llava-v1.6-34b,LLaVA-v1.6-34B,-,-,2024/1,Apache 2.0,LLaVA,https://llava-vl.github.io/blog/2024-01-30-llava-next/
132
- phi-3-mini-4k-instruct-june-2024,Phi-3-Mini-4k-Instruct-June-24,-,0.709,2023/10,MIT,Microsoft,https://huggingface.co/microsoft/Phi-3-mini-4k-instruct
133
- deepseek-v2-api-0628,Deepseek-v2-API-0628,-,-,-,Proprietary,DeepSeek AI,https://platform.deepseek.com/api-docs/updates#deepseek-chat
134
- cogvlm2-llama3-chat-19b,CogVLM2-llama3-chat-19b,-,-,2024/7,CogVLM2,Zhipu AI,https://huggingface.co/THUDM/cogvlm2-llama3-chat-19B
135
- gpt-4o-mini-2024-07-18,GPT-4o-mini-2024-07-18,-,0.820,2023/10,Proprietary,OpenAI,https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
leaderboard_table_20240725.csv DELETED
@@ -1,136 +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
92
- qwen1.5-14b-chat,Qwen1.5-14B-Chat,7.91,0.676,2024/2,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen1.5/
93
- qwen1.5-32b-chat,Qwen1.5-32B-Chat,8.30,0.734,2024/2,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen1.5-32b/
94
- command-r-plus,Command R+,-,-,2024/3,CC-BY-NC-4.0,Cohere,https://txt.cohere.com/command-r-plus-microsoft-azure/
95
- gemma-1.1-7b-it,Gemma-1.1-7B-it,-,0.643,2024/2,Gemma license,Google,https://huggingface.co/google/gemma-1.1-7b-it
96
- dbrx-instruct-preview,DBRX-Instruct-Preview,-,0.737,2023/12,DBRX LICENSE,Databricks,https://www.databricks.com/blog/introducing-dbrx-new-state-art-open-llm
97
- gpt-4-turbo-2024-04-09,GPT-4-Turbo-2024-04-09,-,-,2023/12,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4
98
- gemma-1.1-2b-it,Gemma-1.1-2B-it,-,0.643,2024/2,Gemma license,Google,https://huggingface.co/google/gemma-1.1-2b-it
99
- reka-flash-21b-20240226,Reka-Flash-21B,-,0.735,2023/11,Proprietary,Reka AI,https://www.reka.ai/news/reka-flash-efficient-and-capable-multimodal-language-models
100
- reka-flash-21b-20240226-online,Reka-Flash-21B-online,-,-,Online,Proprietary,Reka AI,https://docs.reka.ai/http-api.html#generation
101
- zephyr-orpo-141b-A35b-v0.1,Zephyr-ORPO-141b-A35b-v0.1,-,-,2024/4,Apache 2.0,HuggingFace,https://huggingface.co/HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1
102
- mixtral-8x22b-instruct-v0.1,Mixtral-8x22b-Instruct-v0.1,-,0.778,2024/4,Apache 2.0,Mistral,https://mistral.ai/news/mixtral-8x22b/
103
- llama-3-70b-instruct,Llama-3-70b-Instruct,-,0.820,2023/12,Llama 3 Community,Meta,https://llama.meta.com/llama3/
104
- llama-3-8b-instruct,Llama-3-8b-Instruct,-,0.684,2023/3,Llama 3 Community,Meta,https://llama.meta.com/llama3/
105
- gemini-1.5-pro-api-0409-preview,Gemini-1.5-Pro-API-0409-Preview,-,0.819,2023/11,Proprietary,Google,https://blog.google/technology/ai/google-gemini-next-generation-model-february-2024/
106
- phi-3-mini-128k-instruct,Phi-3-Mini-128k-Instruct,-,0.681,2023/10,MIT,Microsoft,https://azure.microsoft.com/en-us/blog/introducing-phi-3-redefining-whats-possible-with-slms/
107
- snowflake-arctic-instruct,Snowflake Arctic Instruct,-,0.673,2024/4,Apache 2.0,Snowflake,https://www.snowflake.com/blog/arctic-open-efficient-foundation-language-models-snowflake/
108
- qwen-max-0428,Qwen-Max-0428,-,-,-,Proprietary,Alibaba,https://help.aliyun.com/zh/dashscope/developer-reference/api-details
109
- qwen1.5-110b-chat,Qwen1.5-110B-Chat,8.88,0.804,2024/4,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen1.5-110b/
110
- reka-core-20240501,Reka-Core-20240501,-,0.832,-,Proprietary,Reka AI,https://www.reka.ai/news/reka-core-our-frontier-class-multimodal-language-model
111
- gpt-4o-2024-05-13,GPT-4o-2024-05-13,-,0.887,2023/10,Proprietary,OpenAI,https://openai.com/index/hello-gpt-4o/
112
- phi-3-mini-4k-instruct,Phi-3-Mini-4k-Instruct,-,0.688,2023/10,MIT,Microsoft,https://huggingface.co/microsoft/Phi-3-mini-4k-instruct
113
- yi-large-preview,Yi-Large-preview,-,-,Unknown,Proprietary,01 AI,https://platform.lingyiwanwu.com/docs#%E6%A8%A1%E5%9E%8B
114
- glm-4-0116,GLM-4-0116,-,-,Unknown,Proprietary,Zhipu AI,https://open.bigmodel.cn/
115
- gemini-advanced-0514,Gemini-Advanced-0514,-,-,Online,Proprietary,Google,https://gemini.google.com/advanced
116
- gemini-1.5-pro-api-0514,Gemini-1.5-Pro-API-0514,-,0.859,2023/11,Proprietary,Google,https://deepmind.google/technologies/gemini/pro
117
- gemini-1.5-flash-api-0514,Gemini-1.5-Flash-API-0514,-,0.789,2023/11,Proprietary,Google,https://deepmind.google/technologies/gemini/flash/
118
- yi-34b-chat,Yi-34B-Chat,-,0.735,2023/6,Yi License,01 AI,https://huggingface.co/01-ai/Yi-34B-Chat
119
- yi-1.5-34b-chat,Yi-1.5-34B-Chat,-,0.768,2024/5,Apache-2.0,01 AI,https://huggingface.co/01-ai/Yi-1.5-34B-Chat
120
- phi-3-small-8k-instruct,Phi-3-Small-8k-Instruct,-,0.757,2023/10,MIT,Microsoft,https://huggingface.co/microsoft/Phi-3-small-8k-instruct
121
- phi-3-medium-4k-instruct,Phi-3-Medium-4k-Instruct,-,0.780,2023/10,MIT,Microsoft,https://huggingface.co/microsoft/Phi-3-medium-4k-instruct
122
- qwen2-72b-instruct,Qwen2-72B-Instruct,9.12,0.842,2024/6,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen2/
123
- yi-large,Yi-Large,-,-,Unknown,Proprietary,01 AI,https://platform.01.ai/docs#models-and-pricing
124
- nemotron-4-340b-instruct,Nemotron-4-340B-Instruct,-,-,2023/6,NVIDIA Open Model,Nvidia,https://huggingface.co/nvidia/Nemotron-4-340B-Instruct
125
- reka-flash-preview-20240611,Reka-Flash-Preview-20240611,-,-,-,Proprietary,Reka AI,https://docs.reka.ai/http-api.html#generation
126
- glm-4-0520,GLM-4-0520,-,-,Unknown,Proprietary,Zhipu AI,https://open.bigmodel.cn/dev/api#language
127
- deepseek-coder-v2,DeepSeek-Coder-V2-Instruct,-,-,2024/6,DeepSeek License,DeepSeek AI,https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Instruct
128
- claude-3-5-sonnet-20240620,Claude 3.5 Sonnet,-,0.887,2024/4,Proprietary,Anthropic,https://www.anthropic.com/news/claude-3-5-sonnet
129
- gemma-2-27b-it,Gemma-2-27B-it,-,-,2024/6,Gemma license,Google,https://ai.google.dev/gemma
130
- gemma-2-9b-it,Gemma-2-9B-it,-,-,2024/6,Gemma license,Google,https://ai.google.dev/gemma
131
- llava-v1.6-34b,LLaVA-v1.6-34B,-,-,2024/1,Apache 2.0,LLaVA,https://llava-vl.github.io/blog/2024-01-30-llava-next/
132
- phi-3-mini-4k-instruct-june-2024,Phi-3-Mini-4k-Instruct-June-24,-,0.709,2023/10,MIT,Microsoft,https://huggingface.co/microsoft/Phi-3-mini-4k-instruct
133
- deepseek-v2-api-0628,Deepseek-v2-API-0628,-,-,-,Proprietary,DeepSeek AI,https://platform.deepseek.com/api-docs/updates#deepseek-chat
134
- cogvlm2-llama3-chat-19b,CogVLM2-llama3-chat-19b,-,-,2024/7,CogVLM2,Zhipu AI,https://huggingface.co/THUDM/cogvlm2-llama3-chat-19B
135
- gpt-4o-mini-2024-07-18,GPT-4o-mini-2024-07-18,-,0.820,2023/10,Proprietary,OpenAI,https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/
136
- athene-70b,Athene-70b,-,-,2024/07,CC-BY-NC-4.0,NexusFlow,https://huggingface.co/Nexusflow/Athene-70B
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
leaderboard_table_20240730.csv DELETED
@@ -1,140 +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
92
- qwen1.5-14b-chat,Qwen1.5-14B-Chat,7.91,0.676,2024/2,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen1.5/
93
- qwen1.5-32b-chat,Qwen1.5-32B-Chat,8.30,0.734,2024/2,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen1.5-32b/
94
- command-r-plus,Command R+,-,-,2024/3,CC-BY-NC-4.0,Cohere,https://txt.cohere.com/command-r-plus-microsoft-azure/
95
- gemma-1.1-7b-it,Gemma-1.1-7B-it,-,0.643,2024/2,Gemma license,Google,https://huggingface.co/google/gemma-1.1-7b-it
96
- dbrx-instruct-preview,DBRX-Instruct-Preview,-,0.737,2023/12,DBRX LICENSE,Databricks,https://www.databricks.com/blog/introducing-dbrx-new-state-art-open-llm
97
- gpt-4-turbo-2024-04-09,GPT-4-Turbo-2024-04-09,-,-,2023/12,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4
98
- gemma-1.1-2b-it,Gemma-1.1-2B-it,-,0.643,2024/2,Gemma license,Google,https://huggingface.co/google/gemma-1.1-2b-it
99
- reka-flash-21b-20240226,Reka-Flash-21B,-,0.735,2023/11,Proprietary,Reka AI,https://www.reka.ai/news/reka-flash-efficient-and-capable-multimodal-language-models
100
- reka-flash-21b-20240226-online,Reka-Flash-21B-online,-,-,Online,Proprietary,Reka AI,https://docs.reka.ai/http-api.html#generation
101
- zephyr-orpo-141b-A35b-v0.1,Zephyr-ORPO-141b-A35b-v0.1,-,-,2024/4,Apache 2.0,HuggingFace,https://huggingface.co/HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1
102
- mixtral-8x22b-instruct-v0.1,Mixtral-8x22b-Instruct-v0.1,-,0.778,2024/4,Apache 2.0,Mistral,https://mistral.ai/news/mixtral-8x22b/
103
- llama-3-70b-instruct,Llama-3-70b-Instruct,-,0.820,2023/12,Llama 3 Community,Meta,https://llama.meta.com/llama3/
104
- llama-3-8b-instruct,Llama-3-8b-Instruct,-,0.684,2023/3,Llama 3 Community,Meta,https://llama.meta.com/llama3/
105
- gemini-1.5-pro-api-0409-preview,Gemini-1.5-Pro-API-0409-Preview,-,0.819,2023/11,Proprietary,Google,https://blog.google/technology/ai/google-gemini-next-generation-model-february-2024/
106
- phi-3-mini-128k-instruct,Phi-3-Mini-128k-Instruct,-,0.681,2023/10,MIT,Microsoft,https://azure.microsoft.com/en-us/blog/introducing-phi-3-redefining-whats-possible-with-slms/
107
- snowflake-arctic-instruct,Snowflake Arctic Instruct,-,0.673,2024/4,Apache 2.0,Snowflake,https://www.snowflake.com/blog/arctic-open-efficient-foundation-language-models-snowflake/
108
- qwen-max-0428,Qwen-Max-0428,-,-,-,Proprietary,Alibaba,https://help.aliyun.com/zh/dashscope/developer-reference/api-details
109
- qwen1.5-110b-chat,Qwen1.5-110B-Chat,8.88,0.804,2024/4,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen1.5-110b/
110
- reka-core-20240501,Reka-Core-20240501,-,0.832,-,Proprietary,Reka AI,https://www.reka.ai/news/reka-core-our-frontier-class-multimodal-language-model
111
- gpt-4o-2024-05-13,GPT-4o-2024-05-13,-,0.887,2023/10,Proprietary,OpenAI,https://openai.com/index/hello-gpt-4o/
112
- phi-3-mini-4k-instruct,Phi-3-Mini-4k-Instruct,-,0.688,2023/10,MIT,Microsoft,https://huggingface.co/microsoft/Phi-3-mini-4k-instruct
113
- yi-large-preview,Yi-Large-preview,-,-,Unknown,Proprietary,01 AI,https://platform.lingyiwanwu.com/docs#%E6%A8%A1%E5%9E%8B
114
- glm-4-0116,GLM-4-0116,-,-,Unknown,Proprietary,Zhipu AI,https://open.bigmodel.cn/
115
- gemini-advanced-0514,Gemini-Advanced-0514,-,-,Online,Proprietary,Google,https://gemini.google.com/advanced
116
- gemini-1.5-pro-api-0514,Gemini-1.5-Pro-API-0514,-,0.859,2023/11,Proprietary,Google,https://deepmind.google/technologies/gemini/pro
117
- gemini-1.5-flash-api-0514,Gemini-1.5-Flash-API-0514,-,0.789,2023/11,Proprietary,Google,https://deepmind.google/technologies/gemini/flash/
118
- yi-34b-chat,Yi-34B-Chat,-,0.735,2023/6,Yi License,01 AI,https://huggingface.co/01-ai/Yi-34B-Chat
119
- yi-1.5-34b-chat,Yi-1.5-34B-Chat,-,0.768,2024/5,Apache-2.0,01 AI,https://huggingface.co/01-ai/Yi-1.5-34B-Chat
120
- phi-3-small-8k-instruct,Phi-3-Small-8k-Instruct,-,0.757,2023/10,MIT,Microsoft,https://huggingface.co/microsoft/Phi-3-small-8k-instruct
121
- phi-3-medium-4k-instruct,Phi-3-Medium-4k-Instruct,-,0.780,2023/10,MIT,Microsoft,https://huggingface.co/microsoft/Phi-3-medium-4k-instruct
122
- qwen2-72b-instruct,Qwen2-72B-Instruct,9.12,0.842,2024/6,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen2/
123
- yi-large,Yi-Large,-,-,Unknown,Proprietary,01 AI,https://platform.01.ai/docs#models-and-pricing
124
- nemotron-4-340b-instruct,Nemotron-4-340B-Instruct,-,-,2023/6,NVIDIA Open Model,Nvidia,https://huggingface.co/nvidia/Nemotron-4-340B-Instruct
125
- reka-flash-preview-20240611,Reka-Flash-Preview-20240611,-,-,-,Proprietary,Reka AI,https://docs.reka.ai/http-api.html#generation
126
- glm-4-0520,GLM-4-0520,-,-,Unknown,Proprietary,Zhipu AI,https://open.bigmodel.cn/dev/api#language
127
- deepseek-coder-v2,DeepSeek-Coder-V2-Instruct,-,-,2024/6,DeepSeek License,DeepSeek AI,https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Instruct
128
- claude-3-5-sonnet-20240620,Claude 3.5 Sonnet,-,0.887,2024/4,Proprietary,Anthropic,https://www.anthropic.com/news/claude-3-5-sonnet
129
- gemma-2-27b-it,Gemma-2-27B-it,-,-,2024/6,Gemma license,Google,https://ai.google.dev/gemma
130
- gemma-2-9b-it,Gemma-2-9B-it,-,-,2024/6,Gemma license,Google,https://ai.google.dev/gemma
131
- llava-v1.6-34b,LLaVA-v1.6-34B,-,-,2024/1,Apache 2.0,LLaVA,https://llava-vl.github.io/blog/2024-01-30-llava-next/
132
- phi-3-mini-4k-instruct-june-2024,Phi-3-Mini-4k-Instruct-June-24,-,0.709,2023/10,MIT,Microsoft,https://huggingface.co/microsoft/Phi-3-mini-4k-instruct
133
- deepseek-v2-api-0628,Deepseek-v2-API-0628,-,-,-,Proprietary,DeepSeek AI,https://platform.deepseek.com/api-docs/updates#deepseek-chat
134
- cogvlm2-llama3-chat-19b,CogVLM2-llama3-chat-19b,-,-,2024/7,CogVLM2,Zhipu AI,https://huggingface.co/THUDM/cogvlm2-llama3-chat-19B
135
- gpt-4o-mini-2024-07-18,GPT-4o-mini-2024-07-18,-,0.820,2023/10,Proprietary,OpenAI,https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/
136
- llama-3.1-405b-instruct,Meta-Llama-3.1-405b-Instruct,-,0.886,2023/12,Llama 3.1 Community,Meta,https://ai.meta.com/blog/meta-llama-3-1/
137
- llama-3.1-70b-instruct,Meta-Llama-3.1-70b-Instruct,-,0.860,2023/12,Llama 3.1 Community,Meta,https://ai.meta.com/blog/meta-llama-3-1/
138
- llama-3.1-8b-instruct,Meta-Llama-3.1-8b-Instruct,-,0.730,2023/12,Llama 3.1 Community,Meta,https://ai.meta.com/blog/meta-llama-3-1/
139
- athene-70b-0725,Athene-70b,-,-,2024/7,CC-BY-NC-4.0,NexusFlow,https://huggingface.co/Nexusflow/Athene-70B
140
- internvl2-26b,InternVL2-26b,-,-,2024/7,MIT,OpenGVLab,https://internvl.github.io/blog/2024-07-02-InternVL-2.0/
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
leaderboard_table_20240731.csv DELETED
@@ -1,144 +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
92
- qwen1.5-14b-chat,Qwen1.5-14B-Chat,7.91,0.676,2024/2,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen1.5/
93
- qwen1.5-32b-chat,Qwen1.5-32B-Chat,8.30,0.734,2024/2,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen1.5-32b/
94
- command-r-plus,Command R+,-,-,2024/3,CC-BY-NC-4.0,Cohere,https://txt.cohere.com/command-r-plus-microsoft-azure/
95
- gemma-1.1-7b-it,Gemma-1.1-7B-it,-,0.643,2024/2,Gemma license,Google,https://huggingface.co/google/gemma-1.1-7b-it
96
- dbrx-instruct-preview,DBRX-Instruct-Preview,-,0.737,2023/12,DBRX LICENSE,Databricks,https://www.databricks.com/blog/introducing-dbrx-new-state-art-open-llm
97
- gpt-4-turbo-2024-04-09,GPT-4-Turbo-2024-04-09,-,-,2023/12,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4
98
- gemma-1.1-2b-it,Gemma-1.1-2B-it,-,0.643,2024/2,Gemma license,Google,https://huggingface.co/google/gemma-1.1-2b-it
99
- reka-flash-21b-20240226,Reka-Flash-21B,-,0.735,2023/11,Proprietary,Reka AI,https://www.reka.ai/news/reka-flash-efficient-and-capable-multimodal-language-models
100
- reka-flash-21b-20240226-online,Reka-Flash-21B-online,-,-,Online,Proprietary,Reka AI,https://docs.reka.ai/http-api.html#generation
101
- zephyr-orpo-141b-A35b-v0.1,Zephyr-ORPO-141b-A35b-v0.1,-,-,2024/4,Apache 2.0,HuggingFace,https://huggingface.co/HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1
102
- mixtral-8x22b-instruct-v0.1,Mixtral-8x22b-Instruct-v0.1,-,0.778,2024/4,Apache 2.0,Mistral,https://mistral.ai/news/mixtral-8x22b/
103
- llama-3-70b-instruct,Llama-3-70b-Instruct,-,0.820,2023/12,Llama 3 Community,Meta,https://llama.meta.com/llama3/
104
- llama-3-8b-instruct,Llama-3-8b-Instruct,-,0.684,2023/3,Llama 3 Community,Meta,https://llama.meta.com/llama3/
105
- gemini-1.5-pro-api-0409-preview,Gemini-1.5-Pro-API-0409-Preview,-,0.819,2023/11,Proprietary,Google,https://blog.google/technology/ai/google-gemini-next-generation-model-february-2024/
106
- phi-3-mini-128k-instruct,Phi-3-Mini-128k-Instruct,-,0.681,2023/10,MIT,Microsoft,https://azure.microsoft.com/en-us/blog/introducing-phi-3-redefining-whats-possible-with-slms/
107
- snowflake-arctic-instruct,Snowflake Arctic Instruct,-,0.673,2024/4,Apache 2.0,Snowflake,https://www.snowflake.com/blog/arctic-open-efficient-foundation-language-models-snowflake/
108
- qwen-max-0428,Qwen-Max-0428,-,-,-,Proprietary,Alibaba,https://help.aliyun.com/zh/dashscope/developer-reference/api-details
109
- qwen1.5-110b-chat,Qwen1.5-110B-Chat,8.88,0.804,2024/4,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen1.5-110b/
110
- reka-core-20240501,Reka-Core-20240501,-,0.832,-,Proprietary,Reka AI,https://www.reka.ai/news/reka-core-our-frontier-class-multimodal-language-model
111
- gpt-4o-2024-05-13,GPT-4o-2024-05-13,-,0.887,2023/10,Proprietary,OpenAI,https://openai.com/index/hello-gpt-4o/
112
- phi-3-mini-4k-instruct,Phi-3-Mini-4k-Instruct,-,0.688,2023/10,MIT,Microsoft,https://huggingface.co/microsoft/Phi-3-mini-4k-instruct
113
- yi-large-preview,Yi-Large-preview,-,-,Unknown,Proprietary,01 AI,https://platform.lingyiwanwu.com/docs#%E6%A8%A1%E5%9E%8B
114
- glm-4-0116,GLM-4-0116,-,-,Unknown,Proprietary,Zhipu AI,https://open.bigmodel.cn/
115
- gemini-advanced-0514,Gemini-Advanced-0514,-,-,Online,Proprietary,Google,https://gemini.google.com/advanced
116
- gemini-1.5-pro-api-0514,Gemini-1.5-Pro-API-0514,-,0.859,2023/11,Proprietary,Google,https://deepmind.google/technologies/gemini/pro
117
- gemini-1.5-flash-api-0514,Gemini-1.5-Flash-API-0514,-,0.789,2023/11,Proprietary,Google,https://deepmind.google/technologies/gemini/flash/
118
- yi-34b-chat,Yi-34B-Chat,-,0.735,2023/6,Yi License,01 AI,https://huggingface.co/01-ai/Yi-34B-Chat
119
- yi-1.5-34b-chat,Yi-1.5-34B-Chat,-,0.768,2024/5,Apache-2.0,01 AI,https://huggingface.co/01-ai/Yi-1.5-34B-Chat
120
- phi-3-small-8k-instruct,Phi-3-Small-8k-Instruct,-,0.757,2023/10,MIT,Microsoft,https://huggingface.co/microsoft/Phi-3-small-8k-instruct
121
- phi-3-medium-4k-instruct,Phi-3-Medium-4k-Instruct,-,0.780,2023/10,MIT,Microsoft,https://huggingface.co/microsoft/Phi-3-medium-4k-instruct
122
- qwen2-72b-instruct,Qwen2-72B-Instruct,9.12,0.842,2024/6,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen2/
123
- yi-large,Yi-Large,-,-,Unknown,Proprietary,01 AI,https://platform.01.ai/docs#models-and-pricing
124
- nemotron-4-340b-instruct,Nemotron-4-340B-Instruct,-,-,2023/6,NVIDIA Open Model,Nvidia,https://huggingface.co/nvidia/Nemotron-4-340B-Instruct
125
- reka-flash-preview-20240611,Reka-Flash-Preview-20240611,-,-,-,Proprietary,Reka AI,https://docs.reka.ai/http-api.html#generation
126
- glm-4-0520,GLM-4-0520,-,-,Unknown,Proprietary,Zhipu AI,https://open.bigmodel.cn/dev/api#language
127
- deepseek-coder-v2,DeepSeek-Coder-V2-Instruct,-,-,2024/6,DeepSeek License,DeepSeek AI,https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Instruct
128
- claude-3-5-sonnet-20240620,Claude 3.5 Sonnet,-,0.887,2024/4,Proprietary,Anthropic,https://www.anthropic.com/news/claude-3-5-sonnet
129
- gemma-2-27b-it,Gemma-2-27B-it,-,-,2024/6,Gemma license,Google,https://ai.google.dev/gemma
130
- gemma-2-9b-it,Gemma-2-9B-it,-,-,2024/6,Gemma license,Google,https://ai.google.dev/gemma
131
- llava-v1.6-34b,LLaVA-v1.6-34B,-,-,2024/1,Apache 2.0,LLaVA,https://llava-vl.github.io/blog/2024-01-30-llava-next/
132
- phi-3-mini-4k-instruct-june-2024,Phi-3-Mini-4k-Instruct-June-24,-,0.709,2023/10,MIT,Microsoft,https://huggingface.co/microsoft/Phi-3-mini-4k-instruct
133
- deepseek-v2-api-0628,Deepseek-v2-API-0628,-,-,-,Proprietary,DeepSeek AI,https://platform.deepseek.com/api-docs/updates#deepseek-chat
134
- cogvlm2-llama3-chat-19b,CogVLM2-llama3-chat-19b,-,-,2024/7,CogVLM2,Zhipu AI,https://huggingface.co/THUDM/cogvlm2-llama3-chat-19B
135
- gpt-4o-mini-2024-07-18,GPT-4o-mini-2024-07-18,-,0.820,2023/10,Proprietary,OpenAI,https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/
136
- llama-3.1-405b-instruct,Meta-Llama-3.1-405b-Instruct,-,0.886,2023/12,Llama 3.1 Community,Meta,https://ai.meta.com/blog/meta-llama-3-1/
137
- llama-3.1-70b-instruct,Meta-Llama-3.1-70b-Instruct,-,0.860,2023/12,Llama 3.1 Community,Meta,https://ai.meta.com/blog/meta-llama-3-1/
138
- llama-3.1-8b-instruct,Meta-Llama-3.1-8b-Instruct,-,0.730,2023/12,Llama 3.1 Community,Meta,https://ai.meta.com/blog/meta-llama-3-1/
139
- athene-70b-0725,Athene-70b,-,-,2024/7,CC-BY-NC-4.0,NexusFlow,https://huggingface.co/Nexusflow/Athene-70B
140
- internvl2-26b,InternVL2-26b,-,-,2024/7,MIT,OpenGVLab,https://internvl.github.io/blog/2024-07-02-InternVL-2.0/
141
- gemma-2-2b-it,Gemma-2-2B-it,-,0.513,2024/7,Gemma license,Google,https://ai.google.dev/gemma#introducing-gemma-2
142
- glm-4-air,GLM-4-AIR,-,-,Unknown,Proprietary,Zhipu AI,https://open.bigmodel.cn/
143
- snorkel-mistral-pairrm-dpo,Snorkel-Mistral-PairRM-DPO,-,-,2024/5,Apache 2.0,Snorkel AI,https://huggingface.co/snorkelai/Snorkel-Mistral-PairRM-DPO
144
- mistral-large-2407,Mistral-Large-2407,-,-,2024/7,Proprietary,Mistral,https://mistral.ai/news/mistral-large-2407/
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
leaderboard_table_20240801.csv DELETED
@@ -1,145 +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
92
- qwen1.5-14b-chat,Qwen1.5-14B-Chat,7.91,0.676,2024/2,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen1.5/
93
- qwen1.5-32b-chat,Qwen1.5-32B-Chat,8.30,0.734,2024/2,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen1.5-32b/
94
- command-r-plus,Command R+,-,-,2024/3,CC-BY-NC-4.0,Cohere,https://txt.cohere.com/command-r-plus-microsoft-azure/
95
- gemma-1.1-7b-it,Gemma-1.1-7B-it,-,0.643,2024/2,Gemma license,Google,https://huggingface.co/google/gemma-1.1-7b-it
96
- dbrx-instruct-preview,DBRX-Instruct-Preview,-,0.737,2023/12,DBRX LICENSE,Databricks,https://www.databricks.com/blog/introducing-dbrx-new-state-art-open-llm
97
- gpt-4-turbo-2024-04-09,GPT-4-Turbo-2024-04-09,-,-,2023/12,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4
98
- gemma-1.1-2b-it,Gemma-1.1-2B-it,-,0.643,2024/2,Gemma license,Google,https://huggingface.co/google/gemma-1.1-2b-it
99
- reka-flash-21b-20240226,Reka-Flash-21B,-,0.735,2023/11,Proprietary,Reka AI,https://www.reka.ai/news/reka-flash-efficient-and-capable-multimodal-language-models
100
- reka-flash-21b-20240226-online,Reka-Flash-21B-online,-,-,Online,Proprietary,Reka AI,https://docs.reka.ai/http-api.html#generation
101
- zephyr-orpo-141b-A35b-v0.1,Zephyr-ORPO-141b-A35b-v0.1,-,-,2024/4,Apache 2.0,HuggingFace,https://huggingface.co/HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1
102
- mixtral-8x22b-instruct-v0.1,Mixtral-8x22b-Instruct-v0.1,-,0.778,2024/4,Apache 2.0,Mistral,https://mistral.ai/news/mixtral-8x22b/
103
- llama-3-70b-instruct,Llama-3-70b-Instruct,-,0.820,2023/12,Llama 3 Community,Meta,https://llama.meta.com/llama3/
104
- llama-3-8b-instruct,Llama-3-8b-Instruct,-,0.684,2023/3,Llama 3 Community,Meta,https://llama.meta.com/llama3/
105
- gemini-1.5-pro-api-0409-preview,Gemini-1.5-Pro-API-0409-Preview,-,0.819,2023/11,Proprietary,Google,https://blog.google/technology/ai/google-gemini-next-generation-model-february-2024/
106
- phi-3-mini-128k-instruct,Phi-3-Mini-128k-Instruct,-,0.681,2023/10,MIT,Microsoft,https://azure.microsoft.com/en-us/blog/introducing-phi-3-redefining-whats-possible-with-slms/
107
- snowflake-arctic-instruct,Snowflake Arctic Instruct,-,0.673,2024/4,Apache 2.0,Snowflake,https://www.snowflake.com/blog/arctic-open-efficient-foundation-language-models-snowflake/
108
- qwen-max-0428,Qwen-Max-0428,-,-,-,Proprietary,Alibaba,https://help.aliyun.com/zh/dashscope/developer-reference/api-details
109
- qwen1.5-110b-chat,Qwen1.5-110B-Chat,8.88,0.804,2024/4,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen1.5-110b/
110
- reka-core-20240501,Reka-Core-20240501,-,0.832,-,Proprietary,Reka AI,https://www.reka.ai/news/reka-core-our-frontier-class-multimodal-language-model
111
- gpt-4o-2024-05-13,GPT-4o-2024-05-13,-,0.887,2023/10,Proprietary,OpenAI,https://openai.com/index/hello-gpt-4o/
112
- phi-3-mini-4k-instruct,Phi-3-Mini-4k-Instruct,-,0.688,2023/10,MIT,Microsoft,https://huggingface.co/microsoft/Phi-3-mini-4k-instruct
113
- yi-large-preview,Yi-Large-preview,-,-,Unknown,Proprietary,01 AI,https://platform.lingyiwanwu.com/docs#%E6%A8%A1%E5%9E%8B
114
- glm-4-0116,GLM-4-0116,-,-,Unknown,Proprietary,Zhipu AI,https://open.bigmodel.cn/
115
- gemini-advanced-0514,Gemini-Advanced-0514,-,-,Online,Proprietary,Google,https://gemini.google.com/advanced
116
- gemini-1.5-pro-api-0514,Gemini-1.5-Pro-API-0514,-,0.859,2023/11,Proprietary,Google,https://deepmind.google/technologies/gemini/pro
117
- gemini-1.5-flash-api-0514,Gemini-1.5-Flash-API-0514,-,0.789,2023/11,Proprietary,Google,https://deepmind.google/technologies/gemini/flash/
118
- yi-34b-chat,Yi-34B-Chat,-,0.735,2023/6,Yi License,01 AI,https://huggingface.co/01-ai/Yi-34B-Chat
119
- yi-1.5-34b-chat,Yi-1.5-34B-Chat,-,0.768,2024/5,Apache-2.0,01 AI,https://huggingface.co/01-ai/Yi-1.5-34B-Chat
120
- phi-3-small-8k-instruct,Phi-3-Small-8k-Instruct,-,0.757,2023/10,MIT,Microsoft,https://huggingface.co/microsoft/Phi-3-small-8k-instruct
121
- phi-3-medium-4k-instruct,Phi-3-Medium-4k-Instruct,-,0.780,2023/10,MIT,Microsoft,https://huggingface.co/microsoft/Phi-3-medium-4k-instruct
122
- qwen2-72b-instruct,Qwen2-72B-Instruct,9.12,0.842,2024/6,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen2/
123
- yi-large,Yi-Large,-,-,Unknown,Proprietary,01 AI,https://platform.01.ai/docs#models-and-pricing
124
- nemotron-4-340b-instruct,Nemotron-4-340B-Instruct,-,-,2023/6,NVIDIA Open Model,Nvidia,https://huggingface.co/nvidia/Nemotron-4-340B-Instruct
125
- reka-flash-preview-20240611,Reka-Flash-Preview-20240611,-,-,-,Proprietary,Reka AI,https://docs.reka.ai/http-api.html#generation
126
- glm-4-0520,GLM-4-0520,-,-,Unknown,Proprietary,Zhipu AI,https://open.bigmodel.cn/dev/api#language
127
- deepseek-coder-v2,DeepSeek-Coder-V2-Instruct,-,-,2024/6,DeepSeek License,DeepSeek AI,https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Instruct
128
- claude-3-5-sonnet-20240620,Claude 3.5 Sonnet,-,0.887,2024/4,Proprietary,Anthropic,https://www.anthropic.com/news/claude-3-5-sonnet
129
- gemma-2-27b-it,Gemma-2-27B-it,-,-,2024/6,Gemma license,Google,https://ai.google.dev/gemma
130
- gemma-2-9b-it,Gemma-2-9B-it,-,-,2024/6,Gemma license,Google,https://ai.google.dev/gemma
131
- llava-v1.6-34b,LLaVA-v1.6-34B,-,-,2024/1,Apache 2.0,LLaVA,https://llava-vl.github.io/blog/2024-01-30-llava-next/
132
- phi-3-mini-4k-instruct-june-2024,Phi-3-Mini-4k-Instruct-June-24,-,0.709,2023/10,MIT,Microsoft,https://huggingface.co/microsoft/Phi-3-mini-4k-instruct
133
- deepseek-v2-api-0628,Deepseek-v2-API-0628,-,-,-,DeepSeek,DeepSeek AI,https://platform.deepseek.com/api-docs/updates#deepseek-chat
134
- cogvlm2-llama3-chat-19b,CogVLM2-llama3-chat-19b,-,-,2024/7,CogVLM2,Zhipu AI,https://huggingface.co/THUDM/cogvlm2-llama3-chat-19B
135
- gpt-4o-mini-2024-07-18,GPT-4o-mini-2024-07-18,-,0.820,2023/10,Proprietary,OpenAI,https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/
136
- llama-3.1-405b-instruct,Meta-Llama-3.1-405b-Instruct,-,0.886,2023/12,Llama 3.1 Community,Meta,https://ai.meta.com/blog/meta-llama-3-1/
137
- llama-3.1-70b-instruct,Meta-Llama-3.1-70b-Instruct,-,0.860,2023/12,Llama 3.1 Community,Meta,https://ai.meta.com/blog/meta-llama-3-1/
138
- llama-3.1-8b-instruct,Meta-Llama-3.1-8b-Instruct,-,0.730,2023/12,Llama 3.1 Community,Meta,https://ai.meta.com/blog/meta-llama-3-1/
139
- athene-70b-0725,Athene-70b,-,-,2024/7,CC-BY-NC-4.0,NexusFlow,https://huggingface.co/Nexusflow/Athene-70B
140
- internvl2-26b,InternVL2-26b,-,-,2024/7,MIT,OpenGVLab,https://internvl.github.io/blog/2024-07-02-InternVL-2.0/
141
- gemma-2-2b-it,Gemma-2-2B-it,-,0.513,2024/7,Gemma license,Google,https://ai.google.dev/gemma#introducing-gemma-2
142
- glm-4-air,GLM-4-AIR,-,-,Unknown,Proprietary,Zhipu AI,https://open.bigmodel.cn/
143
- snorkel-mistral-pairrm-dpo,Snorkel-Mistral-PairRM-DPO,-,-,2024/5,Apache 2.0,Snorkel AI,https://huggingface.co/snorkelai/Snorkel-Mistral-PairRM-DPO
144
- mistral-large-2407,Mistral-Large-2407,-,-,2024/7,Proprietary,Mistral,https://mistral.ai/news/mistral-large-2407/
145
- gemini-1.5-pro-exp-0801,Gemini-1.5-Pro-Exp-0801,-,-,-,Proprietary,Google,https://aistudio.google.com/app/prompts/new_chat?model=gemini-1.5-pro-exp-0801