📚 Knowledge · llm-stats.com

MMLU-Pro

Harder 14-subject version of MMLU with ten-way multiple choice.

12
테스트된 모델
Gemini 3 Pro
톱 모델
89.8%
최고 점수
Google
제공업체
#모델명MMLU-Pro제공업체Podium Score
1
89.8%
Google51.9
2
89.6%
Alibaba51.0
3
88.5%
Alibaba42.2
4
88.5%
Alibaba32.4
5
87.8%
Alibaba23.9
6
87.5%
DeepSeek46.0
7
87%
Baidu49.1
8
86.8%
NVIDIA19.0
9
86.7%
Alibaba22.0
10
86.2%
DeepSeek42.0
11
85.2%
Google35.0
12
85%
DeepSeek12.9
벤치마크 데이터는 llm-stats.com에서 집계. 자세한 내용은 방법론.