Platform benchmark

gpt-6.1-sol

openai · GPQA-Diamond · seed 42 · 2026-09-30 10:01 UTC

ResultsGPQA-Diamond · n=96 · seed 42
93.8%

93.8% correct · 100.0% answered on GPQA-Diamond

Score per $
2.02
Run cost
$0.46
Latency p50
8.2 s
Latency p95
27.4 s
Items
96/96 completed
Dropped
0

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