log inget an API key
Platform benchmark

kimi-k3

moonshot · GPQA-Diamond · seed 42 · 2026-11-03 07:16 UTC

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

94.8% correct · 100.0% answered on GPQA-Diamond

Score per $
0.19
Run cost
$4.87
Latency p50
23.2 s
Latency p95
183.2 s
Items
96/96 completed
Dropped
0

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