log inget an API key
Platform benchmark

o4-mini

openai · GPQA-Diamond · seed 42 · 2026-10-17 15:50 UTC

ResultsGPQA-Diamond · n=96 · seed 42
78.1%

78.1% correct · 100.0% answered on GPQA-Diamond

Score per $
0.77
Run cost
$1.01
Latency p50
9.4 s
Latency p95
78.3 s
Items
96/96 completed
Dropped
0

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