Spring Prompt Roasbench - Score: leaderboard
Spring Prompt Roasbench - Score. 2026 v2, twelve-month simulated advertising budget, reproducible seeded scenarios, profit/planning and critical overspend penalties; not comparable to v1. Native score0-100, not actual profit or return on a subscription. Metric: score out of 100. Higher is better.
Metric: score out of 100. Source: springprompt.com. Saturation forecast: Around September 2027. 31 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Fable 5.2 | 61.27 | #1 |
| 2 | GPT-6.1 Terra | 58.41 | #20 |
| 3 | GPT-6 Astra | 56.59 | #6 |
| 4 | Kimi K3.1 Pro | 55.13 | #29 |
| 5 | GPT-6 Sol | 54.11 | #25 |
| 6 | GPT-6 Luna | 53.41 | #95 |
| 7 | Claude Sonnet 5.5 | 52.03 | #19 |
| 8 | Muse Ember | 51.76 | #51 |
| 9 | Claude Opus 5.5 | 51.65 | #5 |
| 10 | Claude Fable 5.1 | 51.54 | #15 |
| 11 | Gemini 3.8 Flash | 51.41 | #36 |
| 12 | Gemini 4 Carbon | 51.22 | #2 |
| 13 | Gemini 4 Argon | 47.02 | #11 |
| 14 | Kimi K3 | 44.06 | #54 |
| 15 | Gemini 3.1 Pro (Preview) | 43.46 | #94 |
No result here: #10 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=spring-prompt-roasbench-score · How It Works · Data refreshed daily, snapshot 2026-11-13.