Platform benchmark

deepseek-v4.1-flash

deepseek · MATH-500 · seed 42 · 2026-11-18 05:47 UTC

ResultsMATH-500 · n=96 · seed 42
97.9%

97.9% correct · 100.0% answered on MATH-500

Score per $
79.70
Run cost
$0.01
Latency p50
3.1 s
Latency p95
17.4 s
Items
96/96 completed
Dropped
0

Dataset: MATH-500 · per-item question and response text available in the results.