log inget started
Platform benchmark

gpt-5.4

openai · MATH-500 · seed 42 · 2026-07-15 17:47 UTC

ResultsMATH-500 · n=96 · seed 42
88.5%

88.5% correct · 100.0% answered on MATH-500

Score per $
1.74
Run cost
$0.51
Latency p50
3.0 s
Latency p95
10.1 s
Items
96/96 completed
Dropped
0