Spring Prompt Bulletbench - Bullet 60s: leaderboard
Spring Prompt Bulletbench - Bullet 60s. Model chess in three separate time controls:10+1Lightning,60sBullet,180+2Blitz. Native ladder Elo and95%CI; not FIDE Elo. Timed-out/invalid moves retain native failure rules. Native best available configuration per clock; all source configurations retained. Metric: ladder Elo. Higher is better.
Metric: ladder Elo. Source: springprompt.com. Saturation forecast: Not forecast. 56 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.8 Flash | 1068 | #36 |
| 2 | GPT-6.1 Sol | 928 | #10 |
| 3 | Gemini 3.1 Flash Lite | 912 | #364 |
| 4 | Gemini 3.5 Flash | 810 | #101 |
| 5 | Gemini 3.5 Flash Lite | 780 | #302 |
| 6 | Gemini 3.6 Flash | 628 | #76 |
| 7 | Mistral Medium 3.5 | 572 | #723 |
| 8 | Jev 1.13 | 572 | #410 |
| 9 | Gemini 3.1 Pro (Preview) | 529 | #94 |
| 10 | Inkling Small | 529 | #294 |
| 11 | Claude Fable 5.2 | 491 | #1 |
| 12 | Mercury 3 | 491 | #200 |
| 13 | Seed 2.0 Mini | 453 | #508 |
| 14 | Claude Haiku 4.5 | 445 | #568 |
| 15 | GPT-6 Sol | 445 | #25 |
No result here: #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=spring-prompt-bulletbench-bullet-60s · How It Works · Data refreshed daily, snapshot 2026-11-13.