log inget an API key
Platform benchmark

gemini-3.1-pro-preview

gemini · GPQA-Diamond · seed 42 · 2026-11-02 06:25 UTC

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

96.9% correct · 100.0% answered on GPQA-Diamond

Score per $
0.19
Run cost
$5.12
Latency p50
25.4 s
Latency p95
132.6 s
Items
96/96 completed
Dropped
0

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