the ai forger
Models
Organizations
Providers
Benchmarks
Compare

MMLU-Pro

general
text
About

MMLU-Pro benchmark

Evaluation Stats
Total Models60
Organizations11
Verified Results0
Self-Reported60
Benchmark Details
Max Score1
Language
en
Performance Overview
Score distribution and top performers

Score Distribution

60 models
Top Score
85.0%
Average Score
63.3%
High Performers (80%+)
6

Top Organizations

#1DeepSeek
4 models
81.5%
#2Moonshot AI
2 models
75.2%
#3OpenAI
2 models
73.6%
#4Anthropic
5 models
68.8%
#5Meta
6 models
68.6%
Leaderboard
Top 20 models ranked by performance
1
85.0%
Raw: 0.85
Self-reported
2
84.0%
Raw: 0.84
Self-reported
3
83.0%
Raw: 0.83
Self-reported
4
81.2%
Raw: 0.812
Self-reported
5
81.1%
Raw: 0.811
Self-reported
6
80.5%
Raw: 0.805
Self-reported
7
77.6%
Raw: 0.776
Self-reported
8
76.4%
Raw: 0.764
Self-reported
9
76.1%
Raw: 0.761
Self-reported
10
76.0%
Raw: 0.76
Self-reported
11
75.9%
Raw: 0.759
Self-reported
12
75.8%
Raw: 0.758
Self-reported
13
75.5%
Raw: 0.755
Self-reported
14
74.7%
Raw: 0.747
Self-reported
15
74.3%
Raw: 0.743
Self-reported
16
74.3%
Raw: 0.743
Self-reported
17
73.3%
Raw: 0.733
Self-reported
18
72.6%
Raw: 0.726
Self-reported
19
72.0%
Raw: 0.72
Self-reported
20
71.6%
Raw: 0.716
Self-reported
Showing top 20 of 60 models