Our new X account is live! Follow @wizwand_team for updates

Mathematical Reasoning on MMLU STEM (test)

82.8Accuracy

Qwen2.5-Math-72B

Updated 4d ago

Evaluation Results

Method	Links
Qwen2.5-Math-72B 2024.09		82.8
Qwen2-72B 2024.09		79.9
Qwen2-Math-72B 2024.09		79.1
Llama-3.1-70B 2024.09		78.1
Qwen2.5-Math-7B 2024.09		67.8
Qwen2-7B 2024.09		67.6
Qwen2-Math-7B 2024.09		65.7
Minerva 2023.10		63.9
InternLM2-Math-Base-20B 2024.09		63
DeepSeek-Coder-V2-Lite-Base 2024.09		59.5
DeepSeekMath-Base-7B 2024.09		56.5
Minerva 2023.10		53.9
Llama-3.1-8B 2024.09		53.1
Qwen2.5-Math-1.5B 2024.09		51.3
Qwen2-Math-1.5B 2024.09		50.4
LLEMMA 2023.10		49
Qwen2-1.5B 2024.09		44.8
Code Llama 2023.10		40.5
LLEMMA 2023.10		37.7
Minerva 2023.10		35.6
Llama 2 2023.10		29.9
Code Llama 2023.10		25.1