Platform benchmark

gpt-5.6-sol

openai · GPQA-Diamond · seed 42 · 2026-07-15 18:55 UTC

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

90.6% correct · 100.0% answered on GPQA-Diamond

Score per $
0.30
Run cost
$2.98
Latency p50
8.8 s
Latency p95
55.8 s
Items
96/96 completed
Dropped
0