Gemini 2.5 Flash (Non-reasoning) — benchmark results

Gemini 2.5 Flash evaluated with reasoning disabled. Provider: Google. Released 2025-06-17. Access: API.

Unified ELO 1523 ± 22, rank #708 of 1776 rated models, from 272 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
EuroEval Spanish NLU - Sentiment Headlines ES52.95Sentiment classification Score (%)97.8
EuroEval Bosnian62.35Average Score (%)97.6
EuroEval Greek NLU - ScaLA EL57.72Linguistic acceptability Score (%)97.5
EuroEval Portuguese Common Sense Reasoning93.06Common Sense Reasoning Average Score (%)96.7
EuroEval Serbian61.96Average Score (%)96.6
EuroEval Albanian56.09Average Score (%)96.5
EuroEval Norwegian Common Sense Reasoning88.29Common Sense Reasoning Average Score (%)96.3
EuroEval Dutch73.91Average Score (%)95.9
EuroEval Icelandic NLU - Hotter and Colder Sentiment58.32Sentiment classification Score (%)95.9
EuroEval Danish Knowledge93.57Knowledge Average Score (%)95.8
EuroEval Finnish65.88Average Score (%)95.6
EuroEval Danish72.17Average Score (%)95.2

Interactive version: theaggregate.ai/model?slug=gemini-2-5-flash-non-reasoning · How the rankings work · Data refreshed daily, snapshot 2026-07-22.