log inget an API key
Platform benchmark

claude-opus-4-7

anthropic · MATH-500 · seed 42 · 2026-11-12 05:01 UTC

ResultsMATH-500 · n=96 · seed 42
93.8%

93.8% correct · 100.0% answered on MATH-500

Score per $
2.84
Run cost
$0.33
Latency p50
1.4 s
Latency p95
7.8 s
Items
96/96 completed
Dropped
0

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