Spring Prompt Surveybench - Analysis Rating: leaderboard
Spring Prompt Surveybench - Analysis Rating. Nine research-analysis tasks, majority of GPT6.1Sol/Opus5.5/Gemini3.1Pro rubric judges, vendor-own judge abstains on paired analysis. Native analysis rating with95%CI; research quality, not token cost. Human-rating sample pending. Metric: rating. Higher is better.
Metric: rating. Source: springprompt.com. Saturation forecast: Around February 2028. 22 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Fable 5.2 | 1662.5 | #1 |
| 2 | Muse Wonder | 1467.9 | #28 |
| 3 | GPT-6.1 Sol | 1445.4 | #10 |
| 4 | Claude Opus 5.5 | 1444.4 | #5 |
| 5 | Muse Ember | 1390.5 | #51 |
| 6 | GPT-6.1 Terra | 1255.8 | #20 |
| 7 | Claude Haiku 5.5 | 1247 | #65 |
| 8 | DeepSeek V4.1 Flash (1017) | 1152 | #39 |
| 9 | GPT-6 Luna | 1100.3 | #95 |
| 10 | Gemini 4 Carbon | 1076 | #2 |
| 11 | Gemini 4 Argon | 959.7 | #11 |
| 12 | Gemini 3.8 Flash | 897.7 | #36 |
| 13 | Mistral Large 4 | 803.9 | #133 |
| 14 | Gemini 3.1 Pro (Preview) | 777.4 | #94 |
| 15 | Mercury 3 | 762.2 | #200 |
No result here: #6 GPT-6 Astra.
Interactive version: theaggregate.ai/benchmark?slug=spring-prompt-surveybench-analysis-rating · How It Works · Data refreshed daily, snapshot 2026-11-13.