the ai forger
Models
Organizations
Providers
Benchmarks
Compare

MMMU

vision
multimodal
About

MMMU benchmark

Evaluation Stats
Total Models52
Organizations11
Verified Results0
Self-Reported50
Benchmark Details
Max Score1
Language
en
Performance Overview
Score distribution and top performers

Score Distribution

52 models
Top Score
84.2%
Average Score
64.1%
High Performers (80%+)
4

Top Organizations

#1Anthropic
3 models
72.6%
#2Moonshot AI
1 model
70.0%
#3Google
11 models
68.9%
#4OpenAI
11 models
66.9%
#5Alibaba
5 models
65.7%
Leaderboard
Top 20 models ranked by performance
1
84.2%
Raw: 0.842
Self-reported
2
82.9%
Raw: 0.829
Self-reported
3
82.0%
Raw: 0.82
Self-reported
4
81.6%
Raw: 0.816
Self-reported
5
79.7%
Raw: 0.797
Self-reported
6
79.6%
Raw: 0.796
Self-reported
7
78.0%
Raw: 0.78
Self-reported
8
77.6%
Raw: 0.776
Self-reported
9
75.4%
Raw: 0.754
Self-reported
10
75.2%
Raw: 0.752
Self-reported
11
75.0%
Raw: 0.75
Self-reported
12
74.8%
Raw: 0.748
Self-reported
13
74.4%
Raw: 0.744
Self-reported
14
73.4%
Raw: 0.734
Self-reported
15
72.9%
Raw: 0.729
Self-reported
16
72.7%
Raw: 0.727
Self-reported
17
72.2%
Raw: 0.722
Self-reported
18
70.7%
Raw: 0.707
Self-reported
19
70.3%
Raw: 0.703
Self-reported
20
70.2%
Raw: 0.702
Self-reported
Showing top 20 of 52 models