log inget an API key
Platform benchmark

claude-haiku-5-5

anthropic · GPQA-Diamond · seed 42 · 2026-11-11 05:10 UTC

ResultsGPQA-Diamond · n=96 · seed 42
87.5%

87.5% correct · 99.0% answered on GPQA-Diamond

Score per $
10.37
Run cost
$0.08
Latency p50
6.0 s
Latency p95
20.5 s
Items
96/96 completed
Dropped
0

Dataset: GPQA-Diamond · question and response text withheld under dataset access terms.