log inget an API key
Platform benchmark

kimi-k3.1-pro

moonshot · GPQA-Diamond · seed 42 · 2026-11-08 07:15 UTC

ResultsGPQA-Diamond · n=96 · seed 42
96.9%

96.9% correct · 100.0% answered on GPQA-Diamond

Score per $
0.27
Run cost
$3.63
Latency p50
23.8 s
Latency p95
227.3 s
Items
96/96 completed
Dropped
0

Dataset: GPQA-Diamond · question and response text withheld under dataset access terms.