Gemini 3.5 Flash (Medium): benchmark results
Gemini 3.5 Flash evaluated at the medium reasoning-effort setting. Provider: Google. Released 2026-05-19. Access: API.
Aggregate Rating 1789 ± 15, rank #159 of 2168 rated models, from 127 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Chess APO Bench | 55.4 | Puzzle accuracy (%) on the 559-puzzle Lichess test split wit | 100 |
| MultiView-Bench - 3D Single View | 33.7 | Accuracy (%; one isometric view only; fraction of 100 proced | 100 |
| Wolfram LLM Benchmarking Project | 70.3 | Correct Functionality (%) | 96.3 |
| Chatbot Arena (Text - Creative Writing) | 1469 | Arena Score | 95.9 |
| Tau2-Bench Telecom | 95.61 | Success Rate (%) | 95.4 |
| AA TAU-2 Bench | 95.61 | Accuracy (%) | 95.3 |
| Chatbot Arena (Text - Writing, Literature & Language) | 1472 | Arena Score | 94.9 |
| Chatbot Arena (Text - Polish) | 1496 | Arena Score | 94.8 |
| Chess Bench LLM | 1944 | Lichess-Classical-calibrated Glicko-2 rating (native signed | 94.7 |
| Chatbot Arena (Text - Entertainment, Sports & Media) | 1457 | Arena Score | 94.6 |
| AA-Omniscience Index - Law | 33.3 | Omniscience Index | 94.3 |
| Chatbot Arena (Text - German) | 1490 | Arena Score | 94.2 |
Interactive version: theaggregate.ai/model?slug=gemini-3-5-flash-medium · How It Works · Data refreshed daily, snapshot 2026-10-20.