the ai forger
Models
Organizations
Providers
Benchmarks
Compare

MMLU

general
text
About

MMLU benchmark

Evaluation Stats
Total Models78
Organizations15
Verified Results0
Self-Reported77
Benchmark Details
Max Score1
Language
en
Performance Overview
Score distribution and top performers

Score Distribution

78 models
Top Score
92.5%
Average Score
79.1%
High Performers (80%+)
45

Top Organizations

#1Moonshot AI
3 models
88.2%
#2DeepSeek
3 models
86.6%
#3xAI
3 models
85.0%
#4Anthropic
5 models
84.4%
#5OpenAI
16 models
84.4%
Leaderboard
Top 20 models ranked by performance
1
92.5%
Raw: 0.925
Self-reported
2
91.8%
Raw: 0.918
Self-reported
3
90.8%
Raw: 0.908
Self-reported
4
90.8%
Raw: 0.908
Self-reported
5
90.8%
Raw: 0.908
Self-reported
6
90.4%
Raw: 0.904
Self-reported
7
90.4%
Raw: 0.904
Self-reported
8
90.2%
Raw: 0.902
Self-reported
9
89.5%
Raw: 0.895
Self-reported
10
88.7%
Raw: 0.887
Self-reported
11
88.5%
Raw: 0.885
Self-reported
12
87.8%
Raw: 0.8781
Self-reported
13
87.8%
Raw: 0.878
Self-reported
14
87.5%
Raw: 0.875
Self-reported
15
87.5%
Raw: 0.875
Self-reported
16
87.4%
Raw: 0.874
Self-reported
17
87.3%
Raw: 0.873
Self-reported
18
86.9%
Raw: 0.869
Self-reported
19
86.8%
Raw: 0.868
Self-reported
20
86.5%
Raw: 0.865
Self-reported
Showing top 20 of 78 models