Platform benchmark

gemini-3.5-flash-lite

gemini · GPQA-Diamond · seed 42 · 2026-10-01 06:30 UTC

ResultsGPQA-Diamond · n=96 · seed 42

80.2%

80.2% correct · 100.0% answered on GPQA-Diamond

Score per $

4.39

Run cost

$0.18

Latency p50

3.7 s

Latency p95

7.7 s

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

Per-item results96 items · tap a row for result details

Question

gemini-3.5-flash-litegemini