Gemini 2.5 Flash (Preview 09-2025) (Thinking) — benchmark results

September 2025 Gemini 2.5 Flash preview snapshot evaluated with thinking enabled. Provider: Google. Released 2025-09-25. Access: API.

Unified ELO 1690 ± 15, rank #293 of 1776 rated models, from 19 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
UGI Leaderboard50.35UGI Score90.2
UGI - Natural Intelligence43.92NatInt Score88.7
UGI - Writing43.88Writing Score84.7
Vals AI LegalBench82.62Accuracy (%)62.4
Vals AI MMMU80.75Accuracy (%)61
Vals AI TaxEval v272.4Accuracy (%)59.4
Vals AI MedQA91.17Accuracy (%)57.4
Vals AI MMLU-Pro83.66Accuracy (%)53.7
Vals AI MedScribe78.5Accuracy (%)51.4
Vals AI LiveCodeBench76.21Accuracy (%)50.4
Vals AI GPQA76.52Accuracy (%)48.4
Vals AI CorpFin v259.75Accuracy (%)47.5

Interactive version: theaggregate.ai/model?slug=gemini-2-5-flash-preview-09-2025-thinking · How the rankings work · Data refreshed daily, snapshot 2026-07-22.