log inget an API key
Platform benchmark

gemini-3.1-pro-preview

gemini · MATH-500 · seed 42 · 2026-11-02 06:24 UTC

ResultsMATH-500 · n=96 · seed 42
96.9%

96.9% correct · 100.0% answered on MATH-500

Score per $
0.44
Run cost
$2.20
Latency p50
9.1 s
Latency p95
67.4 s
Items
96/96 completed
Dropped
0

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