Gemini 3 Flash (Minimal): benchmark results
Provider: Google. Released 2025-12-17. Access: API.
Unified ELO 1648 ± 1, rank #355 of 3078 rated models, from 28 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Pencil Puzzle Bench - Yajilin | 6.7 | Direct-ask Success Rate (%) | 91 |
| Korean CSAT 2026 (Easy Mode) - English | 100 | Points (out of 100) | 90.5 |
| Pencil Puzzle Bench - Tapa | 20 | Direct-ask Success Rate (%) | 89 |
| Korean CSAT 2026 (Easy Mode) - Korean | 99 | Points (out of 100) | 83.3 |
| Pencil Puzzle Bench - Mashu | 6.7 | Direct-ask Success Rate (%) | 82 |
| Pencil Puzzle Bench - Hitori | 20 | Direct-ask Success Rate (%) | 81 |
| Pencil Puzzle Bench - Nurimisaki | 13.3 | Direct-ask Success Rate (%) | 81 |
| Pencil Puzzle Bench - LITS | 6.7 | Direct-ask Success Rate (%) | 78 |
| Korean CSAT 2026 (Easy Mode) - Physics I | 39 | Points (out of 50) | 71.1 |
| Pencil Puzzle Bench - Light Up | 6.7 | Direct-ask Success Rate (%) | 71 |
| Pencil Puzzle Bench - Shikaku | 6.7 | Direct-ask Success Rate (%) | 71 |
| Korean CSAT 2026 (Easy Mode) - Chemistry I | 45 | Points (out of 50) | 63.3 |
Interactive version: theaggregate.ai/model?slug=gemini-3-flash-minimal · How It Works · Data refreshed daily, snapshot 2026-09-19.