log inget an API key
Platform benchmark

claude-opus-4-8

anthropic · MATH-500 · seed 42 · 2026-11-02 05:16 UTC

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

96.9% correct · 100.0% answered on MATH-500

Score per $
2.17
Run cost
$0.45
Latency p50
2.3 s
Latency p95
13.7 s
Items
96/96 completed
Dropped
0

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