log inget an API key
Platform benchmark

claude-sonnet-5

anthropic · GPQA-Diamond · seed 42 · 2026-11-02 05:44 UTC

ResultsGPQA-Diamond · n=96 · seed 42
89.6%

89.6% correct · 97.9% answered on GPQA-Diamond

Score per $
0.35
Run cost
$2.58
Latency p50
12.9 s
Latency p95
170.9 s
Items
96/96 completed
Dropped
0

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