Platform benchmark

qwen3.5-397b-a17b-tee

qwen · MATH-500 · seed 42 · 2026-08-21 17:57 UTC

ResultsMATH-500 · n=96 · seed 42
90.6%

90.6% correct · 99.0% answered on MATH-500

Score per $
0.84
Run cost
$1.07
Latency p50
156.2 s
Latency p95
655.1 s
Items
96/96 completed
Dropped
0

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