Spring Prompt Bulletbench - Lightning 10+1: leaderboard
Spring Prompt Bulletbench - Lightning 10+1. 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. 43 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.5 Flash Lite | 892 | #302 |
| 2 | Gemini 3.1 Flash Lite | 780 | #364 |
| 3 | Gemini 3.5 Flash | 727 | #101 |
| 4 | GPT-6.1 Sol | 584 | #10 |
| 5 | GPT-5.4 Mini | 571 | #389 |
| 6 | Inkling Small | 571 | #294 |
| 7 | Mistral Small 4 | 571 | #1201 |
| 8 | Seed 2.0 Mini | 571 | #508 |
| 9 | Jev 1.13 | 571 | #410 |
| 10 | Mercury 3 | 555 | #200 |
| 11 | Mistral Medium 3.5 | 529 | #723 |
| 12 | GPT-6.1 Terra | 491 | #20 |
| 13 | Mistral Large 4 | 249 | #133 |
| 14 | Gemini 3.8 Flash | 197 | #36 |
| 15 | GPT-5.4 Nano | 197 | #635 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=spring-prompt-bulletbench-lightning-10-plus1 · How It Works · Data refreshed daily, snapshot 2026-11-13.