List your company
ResearchFormerly WizWand

Multitask Language Understanding on CMMLU (test)

78.3AccuracyGPT 4o
23.49237.72151.9566.179Mar 26, 2024Jun 4, 2024Aug 13, 2024Oct 22, 2024Dec 31, 2024Mar 11, 2025May 20, 2025
Updated 8mo ago

Evaluation results

MethodLinks
GPT 4oModel Type=Proprietary2024.1078.3
Baichuan-omniParameters=7B, Modality=Omni-modal2024.1072.2
Qwen-14BShots=5-shot, Model Size Group=13 ~ 20B Models2024.0370.1
InternLM2-20BShots=5-shot, Model Size Group=13 ~ 20B Models2024.0368.7
Qwen1.5-ChatParameters=7B, Modality=Pure text2024.1068
ChatGLM3-6B-BaseShots=5-shot, Model Size Group=<= 7B Models2024.0366.5
InternLM2-7BShots=5-shot, Model Size Group=<= 7B Models2024.0366.3
InternLM2-7B-BaseShots=5-shot, Model Size Group=<= 7B Models2024.0363
InternLM2-20B-BaseShots=5-shot, Model Size Group=13 ~ 20B Models2024.0363
Qwen-7BShots=5-shot, Model Size Group=<= 7B Models2024.0362.5
Baichuan2-13B-BaseShots=5-shot, Model Size Group=13 ~ 20B Models2024.0361.3
Baichuan2-7B-BaseShots=5-shot, Model Size Group=<= 7B Models2024.0357
MAP-NeoParameters=7B, Modality=Pure text2024.1055.1
Mixtral-8x7B-v0.1Shots=5-shot, Model Size Group=13 ~ 20B Models2024.0353.3
CLOBase Model=Qwen2.5-3B, Training Data=English + Chinese2025.0552.1
Llama3-InstructParameters=8B, Modality=Pure text2024.1051.7
VITAParameters=8x7B, Modality=Omni-modal2024.1046.6
SFTBase Model=Qwen2.5-3B, Training Data=English + Chinese2025.0546.34
Mistral-7B-v0.1Shots=5-shot, Model Size Group=<= 7B Models2024.0344.6
CLOBase Model=Llama-3-8B, Training Data=English + Chinese2025.0541.99
SFT+DPOBase Model=Llama-3-8B, Training Data=English + Chinese2025.0540.91
SFTBase Model=Llama-3-8B, Training Data=English + Chinese2025.0539.36
Llama2-13BShots=5-shot, Model Size Group=13 ~ 20B Models2024.0338.8
SFT-tgtBase Model=Llama-3-8B, Training Data=Target language only2025.0538.55
SFT+DPOBase Model=Mistral-7B, Training Data=English + Chinese2025.0537.02
CLOBase Model=Llama-2-13B, Training Data=English + Chinese2025.0534.17
CLOBase Model=Mistral-7B, Training Data=English + Chinese2025.0534.05
SFTBase Model=Mistral-7B, Training Data=English + Chinese2025.0533.74
SFT+DPOBase Model=Llama-2-13B, Training Data=English + Chinese2025.0533.26
SFT-tgtBase Model=Mistral-7B, Training Data=Target language only2025.0533.16
Llama2-7BShots=5-shot, Model Size Group=<= 7B Models2024.0331.9
SFT-tgtBase Model=Llama-2-13B, Training Data=Target language only2025.0531.51
SFTBase Model=Llama-2-13B, Training Data=English + Chinese2025.0531.17
CLOBase Model=Llama-2-7B, Training Data=English + Chinese2025.0528.11
SFT-tgtBase Model=Llama-2-7B, Training Data=Target language only2025.0527.19
SFTBase Model=Llama-2-7B, Training Data=English + Chinese2025.0527.12
SFT+DPOBase Model=Llama-2-7B, Training Data=English + Chinese2025.0526.59
OLMoParameters=7B, Modality=Pure text2024.1025.6