Platform benchmark

claude-sonnet-5

anthropic · GPQA-Diamond · seed 42 · 2026-07-25 00:19 UTC

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

90.6% correct · 99.0% answered on GPQA-Diamond

Score per $
0.17
Run cost
$5.44
Latency p50
13.7 s
Latency p95
186.4 s
Items
96/96 completed
Dropped
0