Gemini 3.5 Flash (High) — benchmark results

Gemini 3.5 Flash evaluated at the high reasoning-effort setting. Provider: Google. Released 2026-05-19. Access: API.

Unified ELO 1928 ± 24, rank #50 of 1776 rated models, from 82 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
AA APEX-Agents47.05Pass@1 (%)100
AA MMMU-Pro84.28Accuracy (%)99.6
Epoch AI - Apex Agents49.6Score99
AA Omniscience - Law57.4Accuracy (%)98.9
AA Omniscience22.68Score98.7
UGI - Writing69.71Writing Score98.7
AA Omniscience - Software Engineering (SWE) - PHP84Accuracy (%)98
UGI - Natural Intelligence68.98NatInt Score97.9
AA Humanity's Last Exam40.96Accuracy (%)97.8
AA GPQA Diamond92.22Accuracy (%)97.2
AA Omniscience - Business45.8Accuracy (%)97.1
AA Omniscience - Humanities & Social Sciences52.3Accuracy (%)97.1

Interactive version: theaggregate.ai/model?slug=gemini-3-5-flash-high · How the rankings work · Data refreshed daily, snapshot 2026-07-22.