Spring Prompt Catalogbench - Reliably Publish Ready: leaderboard
Spring Prompt Catalogbench - Reliably Publish Ready. 56 product briefs,3repeats, factual and sales briefs separately. Reliable publication requires all repeats pass; claims/attributes/channel rubric; majority of three independent judges. Failures stay failed. Native website reports best supported configuration per model; all underlying configurations retained in model_runs. Metric: % of products. Higher is better.
Metric: % of products. Source: springprompt.com. Saturation forecast: Around February 2027. 30 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6 Astra | 75 | #6 |
| 2 | GPT-6.1 Sol | 75 | #10 |
| 3 | Claude Fable 5.2 | 71.43 | #1 |
| 4 | GPT-6 Sol | 66.07 | #25 |
| 5 | Muse Wonder | 66.07 | #28 |
| 6 | GPT-6.1 Terra | 64.29 | #20 |
| 7 | Gemini 4 Argon | 60.71 | #11 |
| 8 | Grok 4.7 | 57.14 | #44 |
| 9 | Claude Opus 5.5 | 55.36 | #5 |
| 10 | GPT-6 Luna | 55.36 | #95 |
| 11 | Gemini 4 Carbon | 53.57 | #2 |
| 12 | Muse Ember | 53.57 | #51 |
| 13 | MiniMax-M3.1-Flash | 50 | #107 |
| 14 | Muse Spark 1.3 | 48.21 | #46 |
| 15 | Gemini 3.1 Pro (Preview) | 44.64 | #94 |
Interactive version: theaggregate.ai/benchmark?slug=spring-prompt-catalogbench-reliably-publish-ready · How It Works · Data refreshed daily, snapshot 2026-11-13.