lmzheng commited on
Commit
a3791fd
1 Parent(s): feb7787

Upload 2 files

Browse files
elo_results_20230717.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae6feeba2538ea2593da1971df50eaa436ab114ba3d91be39de3cf5c692d293f
3
+ size 34065
leaderboard_table_20230717.csv ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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,7.01,1043,0.587,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
11
+ OpenAssistant-LLaMA-30B,6.41,-,0.560,Non-commercial,https://huggingface.co/OpenAssistant/oasst-sft-6-llama-30b-xor
12
+ PaLM-Chat-Bison-001,6.40,1019,-,Proprietary,https://cloud.google.com/vertex-ai/docs/generative-ai/learn/models#foundation_models
13
+ Vicuna-13B,6.39,1055,0.521,Non-commercial,https://huggingface.co/lmsys/vicuna-13b-v1.3
14
+ MPT-30B-chat,6.39,1049,0.504,CC-BY-NC-SA-4.0,https://huggingface.co/mosaicml/mpt-30b-chat
15
+ WizardLM-13B,6.35,-,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
27
+ OpenAssistant-Pythia-12B,4.32,919,0.270,Apache 2.0,https://huggingface.co/OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5
28
+ RWKV-4-Raven-14B,3.98,946,0.256,Apache 2.0,https://huggingface.co/BlinkDL/rwkv-4-raven
29
+ Dolly-V2-12B,3.28,846,0.257,MIT,https://huggingface.co/databricks/dolly-v2-12b
30
+ FastChat-T5-3B,3.04,897,0.477,Apache 2.0,https://huggingface.co/lmsys/fastchat-t5-3b-v1.0
31
+ StableLM-Tuned-Alpha-7B,2.75,867,0.244,CC-BY-NC-SA-4.0,https://huggingface.co/stabilityai/stablelm-tuned-alpha-7b
32
+ LLaMA-13B,2.61,821,0.470,Non-commercial,https://arxiv.org/abs/2302.13971