log inget an API key
Platform benchmark

gemini-3.6-flash

gemini · GPQA-Diamond · seed 42 · 2026-10-01 06:35 UTC

ResultsGPQA-Diamond · n=96 · seed 42
92.7%

92.7% correct · 100.0% answered on GPQA-Diamond

Score per $
0.98
Run cost
$0.94
Latency p50
11.7 s
Latency p95
47.1 s
Items
96/96 completed
Dropped
0

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