Platform benchmark

claude-haiku-4-5

anthropic · MATH-500 · seed 42 · 2026-11-11 05:06 UTC

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

87.5% correct · 100.0% answered on MATH-500

Score per $
2.58
Run cost
$0.34
Latency p50
2.4 s
Latency p95
5.8 s
Items
96/96 completed
Dropped
0

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