log inget an API key
Platform benchmark

claude-sonnet-5

anthropic · GPQA-Diamond · seed 42 · 2026-11-11 05:36 UTC

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

90.6% correct · 97.9% answered on GPQA-Diamond

Score per $
0.20
Run cost
$4.45
Latency p50
13.1 s
Latency p95
238.7 s
Items
96/96 completed
Dropped
0

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