New Release
|
Introducing AI Stats Gateway
|
Read the docs
New Release
Home
Organisations
Models
Benchmarks
API Providers
Home
Organisations
Models
Benchmarks
API Providers
Sign In
Sign In
MATH - Benchmark Leaderboard & Model Performance | AI Stats
MATH
Overview
Overview
Recorded Results
4
Average Score
0.40
Score Range
0.15 - 0.69
Leading Model
0.69 - Mistral Small 3.2
Scores Over Time
Individual benchmark scores plotted by date.
Models Using This Benchmark
Organisation
Model
Reported
Top Score
Info
Self Reported
Source
Mistral
Mistral Small 3.2
20 Jun 2025
0.69
5 Shot CoT
Yes
Source
Google
Gemini 1.0 Ultra
06 Dec 2023
0.53
-
No
Source
xAI
Grok 1
03 Nov 2023
0.24
4 Shot
Yes
Source
xAI
Grok 0
-
0.15
4 Shot
Yes
Source
