CMDB-1500 (Image): leaderboard
Surd AI CMDB-1500 fixed-input decision benchmark: accuracy on 300 image questions spanning candidate choice, yes/no, ordinal and multi-select decisions. The vendor-run leaderboard includes general-purpose LLMs and Surd AI decision models; text and image panels use separate fixed denominators.
Metric: Accuracy (%), fixed denominator of 300 questions (invalid answers count as wrong), effort as labelled. Source: surdai.com. Saturation forecast: Around February 2027. 10 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Claude Sonnet 5.5 | Low | 92.67 | #24 |
| 2 | GPT-6.1 Sol | Low | 92 | #15 |
| 3 | GLM-5.3 Flash | Low | 90.67 | #133 |
| 4 | GPT-6 Luna | Low | 89.33 | #105 |
| 5 | SPX-CD-Pro | 88.67 | ||
| 6 | SPX-CD-Flash | 87.33 | ||
| 7 | Qwen 3.8 Flash | 83 | #125 | |
| 8 | SPX-CD-Omni | 82.67 | ||
| 9 | Kimi K2.6 | 81.33 | #192 | |
| 10 | DeepSeek V4.1 Flash | 79.67 | #67 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=cmdb-1500-image · How It Works · Data refreshed daily, snapshot 2026-11-21.