Share your thoughts, 1 month free Claude Pro on usSee more

Natural Language Reasoning on GSM8K, MATH, SVAMP, ASDiv, MAWPS, and CARP

82.5Average Score

GPT-4

Updated 1mo ago

Evaluation Results

Method	Links
GPT-4 2024.05		82.5
JiuZhang3.0-8x7B 2024.05		79.3
JiuZhang3.0-7B 2024.05		78.8
JiuZhang3.0-8B 2024.05		78.3
DeepSeekMath-7B-RL 2024.05		77.4
MAmmoTH2-8x7B-Plus 2024.05		76.4
Qwen-1.5-110B 2024.05		75.7
MAmmoTH2-7B-Plus 2024.05		75.2
MAmmoTH2-8B-Plus 2024.05		74.6
DeepSeekMath-7B-Instruct 2024.05		73.9
Qwen-1.5-72B 2024.05		72.3
ChatGPT 2024.05		70.7
Math-Shepherd-Mistral-7B 2024.05		68.3
WizardMath-7B-1.1 2024.05		67.6
Abel-7B-002 2024.05		66.4
MetaMath-Mistral-7B 2024.05		65.4
DeepSeekMath-7B 2024.05		65.3
Mixtral-8x7B 2024.05		65.2
Mistral-7B-MMIQC 2024.05		65.2
Rho-1-Math-7B 2024.05		64.3
Intern-Math-20B 2024.05		63.9
Qwen-1.5-7B 2024.05		59.5
Llemma-34B 2024.05		59.1
Gemma-7B 2024.05		56.2
LLAMA-3-8B 2024.05		55.9
InternLM-Math-7B 2024.05		52.8
Llemma-7B 2024.05		49.7
Mistral-7B 2024.05		48.4
DeepSeek-7B 2024.05		31.2