Ludwig Stumpp commited on
Commit
9c17477
1 Parent(s): 21aaac9

Add MMLU few shot

Browse files
Files changed (1) hide show
  1. README.md +39 -38
README.md CHANGED
@@ -8,44 +8,45 @@ https://llm-leaderboard.streamlit.app/
8
 
9
  ## Leaderboard
10
 
11
- | Model Name | Commercial Use? | Chatbot Arena Elo | HumanEval-Python (pass@1) | LAMBADA (zero-shot) | MMLU (zero-shot) | TriviaQA (zero-shot) |
12
- | -------------------------------------------------------------------------------------- | --------------- | ------------------------------------------------ | ------------------------------------------------------------------------------ | --------------------------------------------- | --------------------------------------------------------------------------------------- | --------------------------------------------- |
13
- | [alpaca-13b](https://crfm.stanford.edu/2023/03/13/alpaca.html) | no | [1008](https://lmsys.org/blog/2023-05-03-arena/) | | | | |
14
- | [cerebras-gpt-7b](https://huggingface.co/cerebras/Cerebras-GPT-6.7B) | yes | | | [0.636](https://www.mosaicml.com/blog/mpt-7b) | [0.259](https://www.mosaicml.com/blog/mpt-7b) | [0.141](https://www.mosaicml.com/blog/mpt-7b) |
15
- | [cerebras-gpt-13b](https://huggingface.co/cerebras/Cerebras-GPT-13B) | yes | | | [0.635](https://www.mosaicml.com/blog/mpt-7b) | [0.258](https://www.mosaicml.com/blog/mpt-7b) | [0.146](https://www.mosaicml.com/blog/mpt-7b) |
16
- | [chatglm-6b](https://chatglm.cn/blog) | yes | [985](https://lmsys.org/blog/2023-05-03-arena/) | | | | |
17
- | [chinchilla-70b](https://arxiv.org/abs/2203.15556v1) | no | | | [0.774](https://arxiv.org/abs/2203.15556v1) | | |
18
- | [code-cushman-001](https://arxiv.org/abs/2107.03374) | no | | [33.5](https://drive.google.com/file/d/1cN-b9GnWtHzQRoE7M7gAEyivY0kl4BYs/view) | | | |
19
- | [code-davinci-002](https://arxiv.org/abs/2207.10397v2) | yes | | [65.8](https://arxiv.org/abs/2207.10397v2) | | | |
20
- | [codegen-16B-mono](https://huggingface.co/Salesforce/codegen-16B-mono) | yes | | [29.3](https://drive.google.com/file/d/1cN-b9GnWtHzQRoE7M7gAEyivY0kl4BYs/view) | | | |
21
- | [codegen-16B-multi](https://huggingface.co/Salesforce/codegen-16B-multi) | yes | | [18.3](https://drive.google.com/file/d/1cN-b9GnWtHzQRoE7M7gAEyivY0kl4BYs/view) | | | |
22
- | [codegx-13b](http://keg.cs.tsinghua.edu.cn/codegeex/) | no | | [22.9](https://drive.google.com/file/d/1cN-b9GnWtHzQRoE7M7gAEyivY0kl4BYs/view) | | | |
23
- | [codex-12b](https://arxiv.org/abs/2107.03374v2) | no | | [28.81](https://arxiv.org/abs/2107.03374v2) | | | |
24
- | [dolly-v2-12b](https://huggingface.co/databricks/dolly-v2-12b) | yes | [944](https://lmsys.org/blog/2023-05-03-arena/) | | | | |
25
- | [eleuther-pythia-7b](https://huggingface.co/EleutherAI/pythia-6.9b) | yes | | | [0.667](https://www.mosaicml.com/blog/mpt-7b) | [0.265](https://www.mosaicml.com/blog/mpt-7b) | [0.198](https://www.mosaicml.com/blog/mpt-7b) |
26
- | [eleuther-pythia-12b](https://huggingface.co/EleutherAI/pythia-12b) | yes | | | [0.704](https://www.mosaicml.com/blog/mpt-7b) | [0.253](https://www.mosaicml.com/blog/mpt-7b) | [0.233](https://www.mosaicml.com/blog/mpt-7b) |
27
- | [fastchat-t5-3b](https://huggingface.co/lmsys/fastchat-t5-3b-v1.0) | yes | [951](https://lmsys.org/blog/2023-05-03-arena/) | | | | |
28
- | [gal-120b](https://arxiv.org/abs/2211.09085v1) | no | | | | [52.6](https://paperswithcode.com/paper/galactica-a-large-language-model-for-science-1) | |
29
- | [gpt-3.5-175b](https://arxiv.org/abs/2303.08774v3) | yes | | [48.1](https://arxiv.org/abs/2303.08774v3) | [0.762](https://arxiv.org/abs/2303.08774v3) | | |
30
- | [gpt-4](https://arxiv.org/abs/2303.08774v3) | yes | | [67.0](https://arxiv.org/abs/2303.08774v3) | | | |
31
- | [gpt-neox-20b](https://huggingface.co/EleutherAI/gpt-neox-20b) | yes | | | [0.719](https://www.mosaicml.com/blog/mpt-7b) | [0.269](https://www.mosaicml.com/blog/mpt-7b) | [0.347](https://www.mosaicml.com/blog/mpt-7b) |
32
- | [gpt-j-6b](https://huggingface.co/EleutherAI/gpt-j-6b) | yes | | | [0.683](https://www.mosaicml.com/blog/mpt-7b) | [0.261](https://www.mosaicml.com/blog/mpt-7b) | [0.234](https://www.mosaicml.com/blog/mpt-7b) |
33
- | [koala-13b](https://bair.berkeley.edu/blog/2023/04/03/koala/) | no | [1082](https://lmsys.org/blog/2023-05-03-arena/) | | | | |
34
- | [llama-7b](https://arxiv.org/abs/2302.13971) | no | | [10.5](https://drive.google.com/file/d/1cN-b9GnWtHzQRoE7M7gAEyivY0kl4BYs/view) | [0.738](https://www.mosaicml.com/blog/mpt-7b) | [0.302](https://www.mosaicml.com/blog/mpt-7b) | [0.443](https://www.mosaicml.com/blog/mpt-7b) |
35
- | [llama-13b](https://arxiv.org/abs/2302.13971) | no | [932](https://lmsys.org/blog/2023-05-03-arena/) | [15.8](https://drive.google.com/file/d/1cN-b9GnWtHzQRoE7M7gAEyivY0kl4BYs/view) | | | |
36
- | [llama-33b](https://arxiv.org/abs/2302.13971) | no | | [21.7](https://drive.google.com/file/d/1cN-b9GnWtHzQRoE7M7gAEyivY0kl4BYs/view) | | | |
37
- | [llama-65b](https://arxiv.org/abs/2302.13971) | no | | [23.7](https://drive.google.com/file/d/1cN-b9GnWtHzQRoE7M7gAEyivY0kl4BYs/view) | | | |
38
- | [mpt-7b](https://huggingface.co/mosaicml/mpt-7b) | yes | | | [0.702](https://www.mosaicml.com/blog/mpt-7b) | [0.296](https://www.mosaicml.com/blog/mpt-7b) | [0.343](https://www.mosaicml.com/blog/mpt-7b) |
39
- | [oasst-pythia-12b](https://huggingface.co/OpenAssistant/pythia-12b-pre-v8-12.5k-steps) | yes | [1065](https://lmsys.org/blog/2023-05-03-arena/) | | | | |
40
- | [opt-7b](https://huggingface.co/facebook/opt-6.7b) | no | | | [0.677](https://www.mosaicml.com/blog/mpt-7b) | [0.251](https://www.mosaicml.com/blog/mpt-7b) | [0.227](https://www.mosaicml.com/blog/mpt-7b) |
41
- | [opt-13b](https://huggingface.co/facebook/opt-13b) | no | | | [0.692](https://www.mosaicml.com/blog/mpt-7b) | [0.257](https://www.mosaicml.com/blog/mpt-7b) | [0.282](https://www.mosaicml.com/blog/mpt-7b) |
42
- | [palm-540b](https://arxiv.org/abs/2204.02311v5) | no | | [26.2](https://drive.google.com/file/d/1cN-b9GnWtHzQRoE7M7gAEyivY0kl4BYs/view) | [0.779](https://arxiv.org/abs/2204.02311v5) | | |
43
- | [stablelm-base-alpha-7b](https://huggingface.co/stabilityai/stablelm-base-alpha-7b) | yes | | | [0.533](https://www.mosaicml.com/blog/mpt-7b) | [0.251](https://www.mosaicml.com/blog/mpt-7b) | [0.049](https://www.mosaicml.com/blog/mpt-7b) |
44
- | [stablelm-tuned-alpha-7b](https://huggingface.co/stabilityai/stablelm-tuned-alpha-7b) | no | [858](https://lmsys.org/blog/2023-05-03-arena/) | | | | |
45
- | [starcoder-base-16b](https://huggingface.co/bigcode/starcoderbase) | yes | | [30.4](https://drive.google.com/file/d/1cN-b9GnWtHzQRoE7M7gAEyivY0kl4BYs/view) | | | |
46
- | [starcoder-16b](https://huggingface.co/bigcode/starcoder) | yes | | [33.6](https://drive.google.com/file/d/1cN-b9GnWtHzQRoE7M7gAEyivY0kl4BYs/view) | | | |
47
- | [starcoder-16b (prompted)](https://huggingface.co/bigcode/starcoder) | yes | | [40.8](https://drive.google.com/file/d/1cN-b9GnWtHzQRoE7M7gAEyivY0kl4BYs/view) | | | |
48
- | [vicuna-13b](https://huggingface.co/lmsys/vicuna-13b-delta-v0) | no | [1169](https://lmsys.org/blog/2023-05-03-arena/) | | | | |
 
49
 
50
  ## Benchmarks
51
 
 
8
 
9
  ## Leaderboard
10
 
11
+ | Model Name | Commercial Use? | Chatbot Arena Elo | HumanEval-Python (pass@1) | LAMBADA (zero-shot) | MMLU (zero-shot) | MMLU (few-shot) | TriviaQA (zero-shot) |
12
+ | -------------------------------------------------------------------------------------- | --------------- | ------------------------------------------------ | ------------------------------------------------------------------------------ | --------------------------------------------- | ---------------------------------------------------------------------------------------- | ------------------------------------------- | --------------------------------------------- |
13
+ | [alpaca-13b](https://crfm.stanford.edu/2023/03/13/alpaca.html) | no | [1008](https://lmsys.org/blog/2023-05-03-arena/) | | | | | |
14
+ | [cerebras-gpt-7b](https://huggingface.co/cerebras/Cerebras-GPT-6.7B) | yes | | | [0.636](https://www.mosaicml.com/blog/mpt-7b) | [0.259](https://www.mosaicml.com/blog/mpt-7b) | | [0.141](https://www.mosaicml.com/blog/mpt-7b) |
15
+ | [cerebras-gpt-13b](https://huggingface.co/cerebras/Cerebras-GPT-13B) | yes | | | [0.635](https://www.mosaicml.com/blog/mpt-7b) | [0.258](https://www.mosaicml.com/blog/mpt-7b) | | [0.146](https://www.mosaicml.com/blog/mpt-7b) |
16
+ | [chatglm-6b](https://chatglm.cn/blog) | yes | [985](https://lmsys.org/blog/2023-05-03-arena/) | | | | | |
17
+ | [chinchilla-70b](https://arxiv.org/abs/2203.15556v1) | no | | | [0.774](https://arxiv.org/abs/2203.15556v1) | | [0.675](https://arxiv.org/abs/2203.15556v1) | |
18
+ | [code-cushman-001](https://arxiv.org/abs/2107.03374) | no | | [33.5](https://drive.google.com/file/d/1cN-b9GnWtHzQRoE7M7gAEyivY0kl4BYs/view) | | | | |
19
+ | [code-davinci-002](https://arxiv.org/abs/2207.10397v2) | yes | | [65.8](https://arxiv.org/abs/2207.10397v2) | | | | |
20
+ | [codegen-16B-mono](https://huggingface.co/Salesforce/codegen-16B-mono) | yes | | [29.3](https://drive.google.com/file/d/1cN-b9GnWtHzQRoE7M7gAEyivY0kl4BYs/view) | | | | |
21
+ | [codegen-16B-multi](https://huggingface.co/Salesforce/codegen-16B-multi) | yes | | [18.3](https://drive.google.com/file/d/1cN-b9GnWtHzQRoE7M7gAEyivY0kl4BYs/view) | | | | |
22
+ | [codegx-13b](http://keg.cs.tsinghua.edu.cn/codegeex/) | no | | [22.9](https://drive.google.com/file/d/1cN-b9GnWtHzQRoE7M7gAEyivY0kl4BYs/view) | | | | |
23
+ | [codex-12b](https://arxiv.org/abs/2107.03374v2) | no | | [28.8](https://arxiv.org/abs/2107.03374v2) | | | [0.685](https://arxiv.org/abs/2301.12652v2) | |
24
+ | [dolly-v2-12b](https://huggingface.co/databricks/dolly-v2-12b) | yes | [944](https://lmsys.org/blog/2023-05-03-arena/) | | | | | |
25
+ | [eleuther-pythia-7b](https://huggingface.co/EleutherAI/pythia-6.9b) | yes | | | [0.667](https://www.mosaicml.com/blog/mpt-7b) | [0.265](https://www.mosaicml.com/blog/mpt-7b) | | [0.198](https://www.mosaicml.com/blog/mpt-7b) |
26
+ | [eleuther-pythia-12b](https://huggingface.co/EleutherAI/pythia-12b) | yes | | | [0.704](https://www.mosaicml.com/blog/mpt-7b) | [0.253](https://www.mosaicml.com/blog/mpt-7b) | | [0.233](https://www.mosaicml.com/blog/mpt-7b) |
27
+ | [fastchat-t5-3b](https://huggingface.co/lmsys/fastchat-t5-3b-v1.0) | yes | [951](https://lmsys.org/blog/2023-05-03-arena/) | | | | | |
28
+ | [gal-120b](https://arxiv.org/abs/2211.09085v1) | no | | | | [0.526](https://paperswithcode.com/paper/galactica-a-large-language-model-for-science-1) | | |
29
+ | [gpt-3-175b](https://arxiv.org/abs/2005.14165) | no | | | | | [0.439](https://arxiv.org/abs/2005.14165) | |
30
+ | [gpt-3.5-175b](https://arxiv.org/abs/2303.08774v3) | yes | | [48.1](https://arxiv.org/abs/2303.08774v3) | [0.762](https://arxiv.org/abs/2303.08774v3) | | [0.700](https://arxiv.org/abs/2303.08774v3) | |
31
+ | [gpt-4](https://arxiv.org/abs/2303.08774v3) | yes | | [67.0](https://arxiv.org/abs/2303.08774v3) | | | [0.864](https://arxiv.org/abs/2303.08774v3) | |
32
+ | [gpt-neox-20b](https://huggingface.co/EleutherAI/gpt-neox-20b) | yes | | | [0.719](https://www.mosaicml.com/blog/mpt-7b) | [0.269](https://www.mosaicml.com/blog/mpt-7b) | [0.336](https://arxiv.org/abs/2204.06745v1) | [0.347](https://www.mosaicml.com/blog/mpt-7b) |
33
+ | [gpt-j-6b](https://huggingface.co/EleutherAI/gpt-j-6b) | yes | | | [0.683](https://www.mosaicml.com/blog/mpt-7b) | [0.261](https://www.mosaicml.com/blog/mpt-7b) | | [0.234](https://www.mosaicml.com/blog/mpt-7b) |
34
+ | [koala-13b](https://bair.berkeley.edu/blog/2023/04/03/koala/) | no | [1082](https://lmsys.org/blog/2023-05-03-arena/) | | | | | |
35
+ | [llama-7b](https://arxiv.org/abs/2302.13971) | no | | [10.5](https://drive.google.com/file/d/1cN-b9GnWtHzQRoE7M7gAEyivY0kl4BYs/view) | [0.738](https://www.mosaicml.com/blog/mpt-7b) | [0.302](https://www.mosaicml.com/blog/mpt-7b) | | [0.443](https://www.mosaicml.com/blog/mpt-7b) |
36
+ | [llama-13b](https://arxiv.org/abs/2302.13971) | no | [932](https://lmsys.org/blog/2023-05-03-arena/) | [15.8](https://drive.google.com/file/d/1cN-b9GnWtHzQRoE7M7gAEyivY0kl4BYs/view) | | | | |
37
+ | [llama-33b](https://arxiv.org/abs/2302.13971) | no | | [21.7](https://drive.google.com/file/d/1cN-b9GnWtHzQRoE7M7gAEyivY0kl4BYs/view) | | | | |
38
+ | [llama-65b](https://arxiv.org/abs/2302.13971) | no | | [23.7](https://drive.google.com/file/d/1cN-b9GnWtHzQRoE7M7gAEyivY0kl4BYs/view) | | | [0.634](https://arxiv.org/abs/2302.13971v1) | |
39
+ | [mpt-7b](https://huggingface.co/mosaicml/mpt-7b) | yes | | | [0.702](https://www.mosaicml.com/blog/mpt-7b) | [0.296](https://www.mosaicml.com/blog/mpt-7b) | | [0.343](https://www.mosaicml.com/blog/mpt-7b) |
40
+ | [oasst-pythia-12b](https://huggingface.co/OpenAssistant/pythia-12b-pre-v8-12.5k-steps) | yes | [1065](https://lmsys.org/blog/2023-05-03-arena/) | | | | | |
41
+ | [opt-7b](https://huggingface.co/facebook/opt-6.7b) | no | | | [0.677](https://www.mosaicml.com/blog/mpt-7b) | [0.251](https://www.mosaicml.com/blog/mpt-7b) | | [0.227](https://www.mosaicml.com/blog/mpt-7b) |
42
+ | [opt-13b](https://huggingface.co/facebook/opt-13b) | no | | | [0.692](https://www.mosaicml.com/blog/mpt-7b) | [0.257](https://www.mosaicml.com/blog/mpt-7b) | | [0.282](https://www.mosaicml.com/blog/mpt-7b) |
43
+ | [palm-540b](https://arxiv.org/abs/2204.02311v5) | no | | [26.2](https://drive.google.com/file/d/1cN-b9GnWtHzQRoE7M7gAEyivY0kl4BYs/view) | [0.779](https://arxiv.org/abs/2204.02311v5) | | [0.693](https://arxiv.org/abs/2204.02311v5) | |
44
+ | [stablelm-base-alpha-7b](https://huggingface.co/stabilityai/stablelm-base-alpha-7b) | yes | | | [0.533](https://www.mosaicml.com/blog/mpt-7b) | [0.251](https://www.mosaicml.com/blog/mpt-7b) | | [0.049](https://www.mosaicml.com/blog/mpt-7b) |
45
+ | [stablelm-tuned-alpha-7b](https://huggingface.co/stabilityai/stablelm-tuned-alpha-7b) | no | [858](https://lmsys.org/blog/2023-05-03-arena/) | | | | | |
46
+ | [starcoder-base-16b](https://huggingface.co/bigcode/starcoderbase) | yes | | [30.4](https://drive.google.com/file/d/1cN-b9GnWtHzQRoE7M7gAEyivY0kl4BYs/view) | | | | |
47
+ | [starcoder-16b](https://huggingface.co/bigcode/starcoder) | yes | | [33.6](https://drive.google.com/file/d/1cN-b9GnWtHzQRoE7M7gAEyivY0kl4BYs/view) | | | | |
48
+ | [starcoder-16b (prompted)](https://huggingface.co/bigcode/starcoder) | yes | | [40.8](https://drive.google.com/file/d/1cN-b9GnWtHzQRoE7M7gAEyivY0kl4BYs/view) | | | | |
49
+ | [vicuna-13b](https://huggingface.co/lmsys/vicuna-13b-delta-v0) | no | [1169](https://lmsys.org/blog/2023-05-03-arena/) | | | | | |
50
 
51
  ## Benchmarks
52