Platform benchmark

gemini-3.1-flash-lite

gemini · MATH-500 · seed 42 · 2026-09-04 23:26 UTC

ResultsMATH-500 · n=96 · seed 42
87.5%

87.5% correct · 100.0% answered on MATH-500

Score per $
11.25
Run cost
$0.08
Latency p50
2.8 s
Latency p95
4.4 s
Items
96/96 completed
Dropped
0

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