Gemini 3.5 Flash (Minimal) — benchmark results
Gemini 3.5 Flash evaluated at the minimal reasoning-effort setting. Provider: Google. Released 2026-05-19. Access: API.
Unified ELO 1791 ± 22, rank #148 of 1776 rated models, from 42 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| UGI - Writing | 72.47 | Writing Score | 99.7 |
| UGI - Natural Intelligence | 72.31 | NatInt Score | 98.7 |
| AA Omniscience - Law | 46 | Accuracy (%) | 95.5 |
| AA Omniscience - Humanities & Social Sciences | 45.9 | Accuracy (%) | 94.9 |
| AA Terminal-Bench Hard | 46.21 | Accuracy (%) | 92.9 |
| AA MMMU-Pro | 80.12 | Accuracy (%) | 92.1 |
| AA Omniscience - Business | 36.8 | Accuracy (%) | 92 |
| AA Omniscience - Software Engineering (SWE) - PHP | 68 | Accuracy (%) | 91.3 |
| AA SciCode | 48.84 | Accuracy (%) | 90.8 |
| AA-Omniscience Accuracy | 43.08 | Accuracy (%) | 90.8 |
| AA Omniscience - Software Engineering (SWE) - Julia | 52 | Accuracy (%) | 90.2 |
| AA Omniscience | 1.3 | Score | 87.7 |
Interactive version: theaggregate.ai/model?slug=gemini-3-5-flash-minimal · How the rankings work · Data refreshed daily, snapshot 2026-07-22.