Platform benchmark

gpt-5.4-nano

openai · GPQA-Diamond · seed 42 · 2026-11-11 05:44 UTC

ResultsGPQA-Diamond · n=96 · seed 42
57.3%

57.3% correct · 100.0% answered on GPQA-Diamond

Score per $
9.87
Run cost
$0.06
Latency p50
4.2 s
Latency p95
8.9 s
Items
96/96 completed
Dropped
0

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