log inget an API key
Platform benchmark

o3

openai · GPQA-Diamond · seed 42 · 2026-09-11 13:15 UTC

ResultsGPQA-Diamond · n=96 · seed 42
83.3%

83.3% correct · 100.0% answered on GPQA-Diamond

Score per $
0.27
Run cost
$3.05
Latency p50
24.2 s
Latency p95
145.3 s
Items
96/96 completed
Dropped
0

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