Platform benchmark

o3

openai · MATH-500 · seed 42 · 2026-11-11 06:30 UTC

ResultsMATH-500 · n=96 · seed 42
92.7%

92.7% correct · 100.0% answered on MATH-500

Score per $
0.87
Run cost
$1.07
Latency p50
5.4 s
Latency p95
48.4 s
Items
96/96 completed
Dropped
0

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