Platform benchmark

kimi-k3-tee

moonshot · MATH-500 · seed 42 · 2026-08-21 11:45 UTC

ResultsMATH-500 · n=96 · seed 42
94.8%

94.8% correct · 100.0% answered on MATH-500

Score per $
1.39
Run cost
$0.68
Latency p50
34.2 s
Latency p95
460.5 s
Items
96/96 completed
Dropped
0

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