Platform benchmark

gpt-6-sol

openai · GPQA-Diamond · seed 42 · 2026-11-03 08:45 UTC

ResultsGPQA-Diamond · n=96 · seed 42
92.7%

92.7% correct · 100.0% answered on GPQA-Diamond

Score per $
1.73
Run cost
$0.54
Latency p50
3.9 s
Latency p95
20.1 s
Items
96/96 completed
Dropped
0

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