log inget an API key
Platform benchmark

claude-opus-5-5

anthropic · GPQA-Diamond · seed 42 · 2026-11-02 05:20 UTC

ResultsGPQA-Diamond · n=96 · seed 42
90.6%

90.6% correct · 94.8% answered on GPQA-Diamond

Score per $
0.92
Run cost
$0.98
Latency p50
7.2 s
Latency p95
16.4 s
Items
96/96 completed
Dropped
0

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