Upload leaderboard_table_20230717.csv
Browse files
leaderboard_table_20230717.csv
CHANGED
@@ -1,10 +1,12 @@
|
|
1 |
Model,MT-bench (score),Arena Elo rating,MMLU,License,Link
|
2 |
GPT-4,8.99,1211,0.864,Proprietary,https://openai.com/research/gpt-4
|
|
|
3 |
GPT-3.5-turbo,7.94,1124,0.700,Proprietary,https://openai.com/blog/chatgpt
|
4 |
Claude-v1,7.90,1169,0.756,Proprietary,https://www.anthropic.com/index/introducing-claude
|
5 |
Claude-instant-v1,7.85,1145,0.613,Proprietary,https://www.anthropic.com/index/introducing-claude
|
6 |
Vicuna-33B,7.12,1096,0.592,Non-commercial,https://huggingface.co/lmsys/vicuna-33b-v1.3
|
7 |
WizardLM-30B,7.01,-,0.587,Non-commercial,https://huggingface.co/WizardLM/WizardLM-30B-V1.0
|
|
|
8 |
Guanaco-33B,6.53,1044,0.576,Non-commercial,https://huggingface.co/timdettmers/guanaco-33b-merged
|
9 |
Tulu-30B,6.43,-,0.581,Non-commercial,https://huggingface.co/allenai/tulu-30b
|
10 |
Guanaco-65B,6.41,-,0.621,Non-commercial,https://huggingface.co/timdettmers/guanaco-65b-merged
|
@@ -15,12 +17,14 @@ MPT-30B-chat,6.39,1049,0.504,CC-BY-NC-SA-4.0,https://huggingface.co/mosaicml/mpt
|
|
15 |
WizardLM-13B,6.35,1043,0.523,Non-commercial,https://huggingface.co/WizardLM/WizardLM-13B-V1.0
|
16 |
Vicuna-7B,6.00,1006,0.471,Non-commercial,https://huggingface.co/lmsys/vicuna-7b-v1.3
|
17 |
Baize-v2-13B,5.75,-,0.489,Non-commercial,https://huggingface.co/project-baize/baize-v2-13b
|
|
|
18 |
Nous-Hermes-13B,5.51,-,0.493,Non-commercial,https://huggingface.co/NousResearch/Nous-Hermes-13b
|
19 |
MPT-7B-Chat,5.42,951,0.320,CC-BY-NC-SA-4.0,https://huggingface.co/mosaicml/mpt-7b-chat
|
20 |
GPT4All-13B-Snoozy,5.41,971,0.430,Non-commercial,https://huggingface.co/nomic-ai/gpt4all-13b-snoozy
|
21 |
Koala-13B,5.35,987,0.447,Non-commercial,https://bair.berkeley.edu/blog/2023/04/03/koala/
|
22 |
MPT-30B-Instruct,5.22,-,0.478,CC-BY-SA 3.0,https://huggingface.co/mosaicml/mpt-30b-instruct
|
23 |
Falcon-40B-Instruct,5.17,-,0.547,Apache 2.0,https://huggingface.co/tiiuae/falcon-40b-instruct
|
|
|
24 |
H2O-Oasst-OpenLLaMA-13B,4.63,-,0.428,Apache 2.0,https://huggingface.co/h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-13b
|
25 |
Alpaca-13B,4.53,926,0.481,Non-commercial,https://crfm.stanford.edu/2023/03/13/alpaca.html
|
26 |
ChatGLM-6B,4.50,904,0.361,Non-commercial,https://huggingface.co/THUDM/chatglm-6b
|
|
|
1 |
Model,MT-bench (score),Arena Elo rating,MMLU,License,Link
|
2 |
GPT-4,8.99,1211,0.864,Proprietary,https://openai.com/research/gpt-4
|
3 |
+
Claude-2,8.06,-,-,Proprietary,https://www.anthropic.com/index/claude-2
|
4 |
GPT-3.5-turbo,7.94,1124,0.700,Proprietary,https://openai.com/blog/chatgpt
|
5 |
Claude-v1,7.90,1169,0.756,Proprietary,https://www.anthropic.com/index/introducing-claude
|
6 |
Claude-instant-v1,7.85,1145,0.613,Proprietary,https://www.anthropic.com/index/introducing-claude
|
7 |
Vicuna-33B,7.12,1096,0.592,Non-commercial,https://huggingface.co/lmsys/vicuna-33b-v1.3
|
8 |
WizardLM-30B,7.01,-,0.587,Non-commercial,https://huggingface.co/WizardLM/WizardLM-30B-V1.0
|
9 |
+
WizardLM-13B-v1.1,6.76,-,-,Non-commercial,https://huggingface.co/WizardLM/WizardLM-13B-V1.1
|
10 |
Guanaco-33B,6.53,1044,0.576,Non-commercial,https://huggingface.co/timdettmers/guanaco-33b-merged
|
11 |
Tulu-30B,6.43,-,0.581,Non-commercial,https://huggingface.co/allenai/tulu-30b
|
12 |
Guanaco-65B,6.41,-,0.621,Non-commercial,https://huggingface.co/timdettmers/guanaco-65b-merged
|
|
|
17 |
WizardLM-13B,6.35,1043,0.523,Non-commercial,https://huggingface.co/WizardLM/WizardLM-13B-V1.0
|
18 |
Vicuna-7B,6.00,1006,0.471,Non-commercial,https://huggingface.co/lmsys/vicuna-7b-v1.3
|
19 |
Baize-v2-13B,5.75,-,0.489,Non-commercial,https://huggingface.co/project-baize/baize-v2-13b
|
20 |
+
XGen-7B-8K-Inst,5.55,-,-,Non-commercial,https://huggingface.co/Salesforce/xgen-7b-8k-inst
|
21 |
Nous-Hermes-13B,5.51,-,0.493,Non-commercial,https://huggingface.co/NousResearch/Nous-Hermes-13b
|
22 |
MPT-7B-Chat,5.42,951,0.320,CC-BY-NC-SA-4.0,https://huggingface.co/mosaicml/mpt-7b-chat
|
23 |
GPT4All-13B-Snoozy,5.41,971,0.430,Non-commercial,https://huggingface.co/nomic-ai/gpt4all-13b-snoozy
|
24 |
Koala-13B,5.35,987,0.447,Non-commercial,https://bair.berkeley.edu/blog/2023/04/03/koala/
|
25 |
MPT-30B-Instruct,5.22,-,0.478,CC-BY-SA 3.0,https://huggingface.co/mosaicml/mpt-30b-instruct
|
26 |
Falcon-40B-Instruct,5.17,-,0.547,Apache 2.0,https://huggingface.co/tiiuae/falcon-40b-instruct
|
27 |
+
ChatGLM2-6B,4.96,-,-,Apache-2.0,https://huggingface.co/THUDM/chatglm2-6b
|
28 |
H2O-Oasst-OpenLLaMA-13B,4.63,-,0.428,Apache 2.0,https://huggingface.co/h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-13b
|
29 |
Alpaca-13B,4.53,926,0.481,Non-commercial,https://crfm.stanford.edu/2023/03/13/alpaca.html
|
30 |
ChatGLM-6B,4.50,904,0.361,Non-commercial,https://huggingface.co/THUDM/chatglm-6b
|