log inget an API key
Platform benchmark

gemma-4-31b-turbo-tee

google · MATH-500 · seed 42 · 2026-10-01 06:44 UTC

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

96.9% correct · 100.0% answered on MATH-500

Score per $
79.45
Run cost
$0.01
Latency p50
13.7 s
Latency p95
52.9 s
Items
96/96 completed
Dropped
0

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