log inget an API key
Platform benchmark

kimi-k3

moonshot · GPQA-Diamond · seed 42 · 2026-11-11 05:39 UTC

ResultsGPQA-Diamond · n=96 · seed 42
94.8%

94.8% correct · 100.0% answered on GPQA-Diamond

Score per $
0.23
Run cost
$4.17
Latency p50
28.7 s
Latency p95
280.6 s
Items
96/96 completed
Dropped
0

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