Gemini 3.5 Flash — benchmark results

Google's speed-oriented Gemini 3.5 Flash model, balancing capability with lower latency. Provider: Google. Released 2026-05-19. Access: API.

Unified ELO 1887 ± 14, rank #71 of 1776 rated models, from 204 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
AI for Education Visual Reasoning86Accuracy (%)100
AI for Education Visual Reasoning - match (figure)85.2Accuracy (%)100
AI for Education Visual Reasoning - reasoning by analogy88.8Accuracy (%)100
APEX-Agents66.1Mean Score (ReAct) (self-reported)100
APEX-Agents-AA47.1Pass@1 (self-reported)100
Arabic Broad Leaderboard9.25Average Score (0-10)100
Benchmarks.bio - BioSecBench-Refusal51.5Pass Rate (%)100
CAIS Vision Capabilities Index65.7Vision Capabilities Index (self-reported)100
Finance Agent v257.9Score (self-reported)100
HieroglyphBench52.5Sign accuracy (%)100
MCP Atlas83.6Score (self-reported)100
Vals AI Finance Agent v257.86Accuracy (%)100

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