weichiang commited on
Commit
8166dd6
β€’
1 Parent(s): 75e958e

update 1116

Browse files
elo_results_20231116.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0072e5bdcee16d0d2db6ae0a6c7c450e0c4ce66188dc3e3a65d6ee24e8391152
3
+ size 39363
leaderboard_table_20231116.csv ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Model,MT-bench (score),Arena Elo rating,MMLU,License,Link
2
+ WizardLM-30B,7.01,-,0.587,Non-commercial,https://huggingface.co/WizardLM/WizardLM-30B-V1.0
3
+ Vicuna-13B-16k,6.92,-,0.545,Llama 2 Community,https://huggingface.co/lmsys/vicuna-13b-v1.5-16k
4
+ WizardLM-13B-v1.1,6.76,-,0.500,Non-commercial,https://huggingface.co/WizardLM/WizardLM-13B-V1.1
5
+ Tulu-30B,6.43,-,0.581,Non-commercial,https://huggingface.co/allenai/tulu-30b
6
+ Guanaco-65B,6.41,-,0.621,Non-commercial,https://huggingface.co/timdettmers/guanaco-65b-merged
7
+ OpenAssistant-LLaMA-30B,6.41,-,0.560,Non-commercial,https://huggingface.co/OpenAssistant/oasst-sft-6-llama-30b-xor
8
+ WizardLM-13B-v1.0,6.35,-,0.523,Non-commercial,https://huggingface.co/WizardLM/WizardLM-13B-V1.0
9
+ Vicuna-7B-16k,6.22,-,0.485,Llama 2 Community,https://huggingface.co/lmsys/vicuna-7b-v1.5-16k
10
+ Baize-v2-13B,5.75,-,0.489,Non-commercial,https://huggingface.co/project-baize/baize-v2-13b
11
+ XGen-7B-8K-Inst,5.55,-,0.421,Non-commercial,https://huggingface.co/Salesforce/xgen-7b-8k-inst
12
+ Nous-Hermes-13B,5.51,-,0.493,Non-commercial,https://huggingface.co/NousResearch/Nous-Hermes-13b
13
+ MPT-30B-Instruct,5.22,-,0.478,CC-BY-SA 3.0,https://huggingface.co/mosaicml/mpt-30b-instruct
14
+ Falcon-40B-Instruct,5.17,-,0.547,Apache 2.0,https://huggingface.co/tiiuae/falcon-40b-instruct
15
+ H2O-Oasst-OpenLLaMA-13B,4.63,-,0.428,Apache 2.0,https://huggingface.co/h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-13b
16
+ GPT-4-Turbo,9.32,1210,-,Proprietary,https://openai.com/blog/new-models-and-developer-products-announced-at-devday
17
+ GPT-4,8.99,1159,0.864,Proprietary,https://openai.com/research/gpt-4
18
+ Claude-1,7.90,1146,0.770,Proprietary,https://www.anthropic.com/index/introducing-claude
19
+ Claude-2,8.06,1125,0.785,Proprietary,https://www.anthropic.com/index/claude-2
20
+ Claude-instant-1,7.85,1106,0.734,Proprietary,https://www.anthropic.com/index/introducing-claude
21
+ GPT-3.5-turbo,7.94,1103,0.700,Proprietary,https://openai.com/blog/chatgpt
22
+ WizardLM-70b-v1.0,7.71,1093,0.637,Llama 2 Community,https://huggingface.co/WizardLM/WizardLM-70B-V1.0
23
+ Vicuna-33B,7.12,1090,0.592,Non-commercial,https://huggingface.co/lmsys/vicuna-33b-v1.3
24
+ Llama-2-70b-chat,6.86,1065,0.630,Llama 2 Community,https://huggingface.co/meta-llama/Llama-2-70b-chat-hf
25
+ OpenChat-3.5,7.81,1070,0.643,Apache-2.0,https://huggingface.co/openchat/openchat_3.5
26
+ WizardLM-13b-v1.2,7.20,1047,0.527,Llama 2 Community,https://huggingface.co/WizardLM/WizardLM-13B-V1.2
27
+ zephyr-7b-beta,7.34,1042,0.614,MIT,https://huggingface.co/HuggingFaceH4/zephyr-7b-beta
28
+ MPT-30B-chat,6.39,1031,0.504,CC-BY-NC-SA-4.0,https://huggingface.co/mosaicml/mpt-30b-chat
29
+ Vicuna-13B,6.57,1031,0.558,Llama 2 Community,https://huggingface.co/lmsys/vicuna-13b-v1.5
30
+ QWen-Chat-14B,6.96,1030,0.665,Qianwen LICENSE,https://huggingface.co/Qwen/Qwen-14B-Chat
31
+ falcon-180b-chat,-,1024,0.680,Falcon-180B TII License,https://huggingface.co/tiiuae/falcon-180B-chat
32
+ zephyr-7b-alpha,6.88,1024,-,MIT,https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha
33
+ CodeLlama-34B-instruct,-,1022,0.537,Llama 2 Community,https://huggingface.co/codellama/CodeLlama-34b-Instruct-hf
34
+ Guanaco-33B,6.53,1021,0.576,Non-commercial,https://huggingface.co/timdettmers/guanaco-33b-merged
35
+ Llama-2-13b-chat,6.65,1021,0.536,Llama 2 Community,https://huggingface.co/meta-llama/Llama-2-13b-chat-hf
36
+ Mistral-7B-Instruct-v0.1,6.84,1008,0.554,Apache 2.0,https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1
37
+ Llama-2-7b-chat,6.27,1001,0.458,Llama 2 Community,https://huggingface.co/meta-llama/Llama-2-7b-chat-hf
38
+ Vicuna-7B,6.17,994,0.498,Llama 2 Community,https://huggingface.co/lmsys/vicuna-7b-v1.5
39
+ PaLM-Chat-Bison-001,6.40,991,-,Proprietary,https://cloud.google.com/vertex-ai/docs/generative-ai/learn/models#foundation_models
40
+ Koala-13B,5.35,955,0.447,Non-commercial,https://bair.berkeley.edu/blog/2023/04/03/koala/
41
+ ChatGLM3-6B,-,970,-,Apache-2.0,https://huggingface.co/THUDM/chatglm3-6b
42
+ GPT4All-13B-Snoozy,5.41,925,0.430,Non-commercial,https://huggingface.co/nomic-ai/gpt4all-13b-snoozy
43
+ MPT-7B-Chat,5.42,918,0.320,CC-BY-NC-SA-4.0,https://huggingface.co/mosaicml/mpt-7b-chat
44
+ ChatGLM2-6B,4.96,918,0.455,Apache-2.0,https://huggingface.co/THUDM/chatglm2-6b
45
+ RWKV-4-Raven-14B,3.98,915,0.256,Apache 2.0,https://huggingface.co/BlinkDL/rwkv-4-raven
46
+ Alpaca-13B,4.53,893,0.481,Non-commercial,https://crfm.stanford.edu/2023/03/13/alpaca.html
47
+ OpenAssistant-Pythia-12B,4.32,884,0.270,Apache 2.0,https://huggingface.co/OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5
48
+ ChatGLM-6B,4.50,871,0.361,Non-commercial,https://huggingface.co/THUDM/chatglm-6b
49
+ FastChat-T5-3B,3.04,863,0.477,Apache 2.0,https://huggingface.co/lmsys/fastchat-t5-3b-v1.0
50
+ StableLM-Tuned-Alpha-7B,2.75,833,0.244,CC-BY-NC-SA-4.0,https://huggingface.co/stabilityai/stablelm-tuned-alpha-7b
51
+ Dolly-V2-12B,3.28,810,0.257,MIT,https://huggingface.co/databricks/dolly-v2-12b
52
+ LLaMA-13B,2.61,789,0.470,Non-commercial,https://arxiv.org/abs/2302.13971