CDH-Bench (Multiple-Choice QA) - Relational Anomalies: leaderboard
Metric: Counterfactual accuracy (%) on the 100 relational-anomaly images (reversed behavioural, spatial, size or causal relations such as mice hunting a cat), choosing among four shuffled options: the answer the image shows, the commonsense alternative as an explicit distractor and two other plausible distractors; each image is shown alone, without its matched commonsense twin, under one prompt per format; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 82 | #54 |
| 2 | Kimi K2.5 | 78 | #139 |
| 3 | Gemini 3.1 Flash Lite (Preview) | 77 | #186 |
| 4 | Qwen 3.5 Plus | 72.92 | #123 |
| 5 | GPT-5.4 | 70.71 | #76 |
| 6 | Doubao-Seed-1-8-251228 | 69 | #146 |
| 7 | GPT-5.4 Mini | 64 | #202 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=cdh-bench-multiple-choice-qa-relational-anomalies · How It Works · Data refreshed daily, snapshot 2026-10-11.