log inget an API key
Platform benchmark

gemini-3.1-flash-lite

gemini · GPQA-Diamond · seed 42 · 2026-09-04 23:26 UTC

ResultsGPQA-Diamond · n=96 · seed 42
75.0%

75.0% correct · 100.0% answered on GPQA-Diamond

Score per $
8.12
Run cost
$0.09
Latency p50
3.2 s
Latency p95
5.4 s
Items
96/96 completed
Dropped
0

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