Skip to content

Benchmark

MathArena Miklós Schweitzer 2025

Math benchmarks measure how well models solve maths problems. Scores are percentages.

Models measured
1
Scores recorded
1
Sources
1
IQ weight
No weight published

Score distribution

90%
Mean
90%
Median
0%
Std dev
90%
10th percentile
90%
90th percentile
90%
Min

Leaderboard

#Model
1GPT-5 Pro· MathArena data90%

Tokens the model generated per task, as measured by the source. Comparable within this benchmark only.

Data credits: MathArena (ETH SRI / INSAIT), MIT — cite dekoninck2026matharena (licence)