HiddenMath

math
text
About

HiddenMath benchmark

Evaluation Stats
Total Models13
Organizations1
Verified Results0
Self-Reported13
Benchmark Details
Max Score1
Language
en
Performance Overview
Score distribution and top performers

Score Distribution

13 models
Top Score
63.0%
Average Score
42.7%
High Performers (80%+)
0

Top Organizations

#1Google
13 models
42.7%
Leaderboard
Top 13 models ranked by performance
63.0%
Raw: 0.63
Self-reported
60.3%
Raw: 0.603
Self-reported
55.3%
Raw: 0.553
Self-reported
54.5%
Raw: 0.545
Self-reported
52.0%
Raw: 0.52
Self-reported
47.2%
Raw: 0.472
Self-reported
43.0%
Raw: 0.43
Self-reported
37.7%
Raw: 0.377
Self-reported
37.7%
Raw: 0.377
Self-reported
32.8%
Raw: 0.328
Self-reported
27.7%
Raw: 0.277
Self-reported
27.7%
Raw: 0.277
Self-reported
15.8%
Raw: 0.158
Self-reported