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
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA APEX-Agents | 47.05 | Pass@1 (%) | 100 |
| AA MMMU-Pro | 84.28 | Accuracy (%) | 99.6 |
| Epoch AI - Apex Agents | 49.6 | Score | 99 |
| AA Omniscience - Law | 57.4 | Accuracy (%) | 98.9 |
| AA Omniscience | 22.68 | Score | 98.7 |
| UGI - Writing | 69.71 | Writing Score | 98.7 |
| AA Omniscience - Software Engineering (SWE) - PHP | 84 | Accuracy (%) | 98 |
| UGI - Natural Intelligence | 68.98 | NatInt Score | 97.9 |
| AA Humanity's Last Exam | 40.96 | Accuracy (%) | 97.8 |
| AA GPQA Diamond | 92.22 | Accuracy (%) | 97.2 |
| AA Omniscience - Business | 45.8 | Accuracy (%) | 97.1 |
| AA Omniscience - Humanities & Social Sciences | 52.3 | Accuracy (%) | 97.1 |
Interactive version: theaggregate.ai/model?slug=gemini-3-5-flash-high · How the rankings work · Data refreshed daily, snapshot 2026-07-22.