log inget an API key
Platform benchmark

claude-opus-4-7

anthropic · GPQA-Diamond · seed 42 · 2026-11-10 05:18 UTC

ResultsGPQA-Diamond · n=96 · seed 42
93.8%

93.8% correct · 99.0% answered on GPQA-Diamond

Score per $
0.32
Run cost
$2.89
Latency p50
4.5 s
Latency p95
46.4 s
Items
96/96 completed
Dropped
0

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