Platform benchmark

deepseek-v4.1-flash

deepseek · MATH-500 · seed 42 · 2026-10-25 06:13 UTC

ResultsMATH-500 · n=96 · seed 42
99.0%

99.0% correct · 100.0% answered on MATH-500

Score per $
21.49
Run cost
$0.05
Latency p50
2.7 s
Latency p95
27.1 s
Items
96/96 completed
Dropped
0

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