Spring Prompt Bulletbench - Blitz 3+2: leaderboard
Spring Prompt Bulletbench - Blitz 3+2. 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: Around July 2028. 18 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 4 Argon | 1147 | #11 |
| 2 | Gemini 3.8 Flash | 1126 | #36 |
| 3 | Claude Fable 5.2 | 1100 | #1 |
| 4 | GPT-6.1 Sol | 927 | #10 |
| 5 | Gemini 4 Carbon | 848 | #2 |
| 6 | GPT-6 Astra | 839 | #6 |
| 7 | Gemini 3.5 Flash Lite | 707 | #302 |
| 8 | Gemini 3.1 Pro (Preview) | 683 | #94 |
| 9 | GPT-6.1 Terra | 683 | #20 |
| 10 | Claude Opus 5.5 | 557 | #5 |
| 11 | GPT-6 Luna | 557 | #95 |
| 12 | Claude Sonnet 5.5 | 557 | #19 |
| 13 | Claude Haiku 5.5 | 557 | #65 |
| 14 | Mistral Medium 3.5 | 555 | #723 |
| 15 | Mistral Large 4 | 555 | #133 |
Interactive version: theaggregate.ai/benchmark?slug=spring-prompt-bulletbench-blitz-3-plus2 · How It Works · Data refreshed daily, snapshot 2026-11-13.