the ai forger
Models
Organizations
Providers
Benchmarks
Compare

MGSM

math
text
About

MGSM benchmark

Evaluation Stats
Total Models31
Organizations6
Verified Results0
Self-Reported30
Benchmark Details
Max Score1
Language
en
Performance Overview
Score distribution and top performers

Score Distribution

31 models
Top Score
92.3%
Average Score
77.9%
High Performers (80%+)
19

Top Organizations

#1Anthropic
6 models
86.4%
#2OpenAI
8 models
83.6%
#3Alibaba
1 model
83.5%
#4Meta
6 models
81.3%
#5Google
6 models
67.3%
Leaderboard
Top 20 models ranked by performance
1
92.3%
Raw: 0.923
Self-reported
2
92.0%
Raw: 0.92
Self-reported
3
91.6%
Raw: 0.916
Self-reported
4
91.6%
Raw: 0.916
Self-reported
5
91.1%
Raw: 0.911
Self-reported
6
90.8%
Raw: 0.908
Self-reported
7
90.7%
Raw: 0.907
Self-reported
8
90.6%
Raw: 0.906
Self-reported
9
90.5%
Raw: 0.905
Self-reported
10
89.3%
Raw: 0.893
Self-reported
11
88.5%
Raw: 0.885
Self-reported
12
87.5%
Raw: 0.875
Self-reported
13
87.0%
Raw: 0.87
Self-reported
14
86.9%
Raw: 0.869
Self-reported
15
85.6%
Raw: 0.856
Self-reported
16
83.5%
Raw: 0.8353
Self-reported
17
83.5%
Raw: 0.835
Self-reported
18
82.6%
Raw: 0.826
Self-reported
19
80.6%
Raw: 0.806
Self-reported
20
75.1%
Raw: 0.751
Self-reported
Showing top 20 of 31 models