Platform benchmark

o4-mini

openai · MATH-500 · seed 42 · 2026-10-17 15:47 UTC

ResultsMATH-500 · n=96 · seed 42
93.8%

93.8% correct · 100.0% answered on MATH-500

Score per $
2.67
Run cost
$0.35
Latency p50
4.5 s
Latency p95
23.3 s
Items
96/96 completed
Dropped
0

Dataset: MATH-500 · per-item question and response text available in the results.