Gemini 3.5 Flash Lite (High): benchmark results
Provider: Google. Released 2026-07-21. Access: API.
Unified ELO 1654 ± 1, rank #311 of 3081 rated models, from 71 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Korean CSAT 2026 (Easy Mode) - Chemistry I | 50 | Points (out of 50) | 90.8 |
| Vals AI MortgageTax | 68.68 | Accuracy (%) | 87.6 |
| Korean CSAT 2026 (Easy Mode) - Physics I | 43 | Points (out of 50) | 81 |
| ZeroBench | 14 | Score (%) | 75.4 |
| Vals AI LegalBench | 84.07 | Accuracy (%) | 75.3 |
| Korean CSAT 2026 (Easy Mode) - Life Science I | 45 | Points (out of 50) | 74.5 |
| IOI | 26.17 | Score (self-reported) | 74.2 |
| LiveBench Simplify | 68.02 | Score | 71.9 |
| Korean CSAT 2026 (Easy Mode) - Total | 422.67 | Points (out of 450) | 70.1 |
| Epoch AI - Dtbench | 83.47 | Score | 69.4 |
| Epoch AI - GPQA Diamond | 83.33 | Accuracy (%) | 68.1 |
| Korean CSAT 2026 (Easy Mode) - Society and Culture | 42 | Points (out of 50) | 68 |
Interactive version: theaggregate.ai/model?slug=gemini-3-5-flash-lite-high · How It Works · Data refreshed daily, snapshot 2026-09-21.