CVT-Bench - Synthetic Isolated F1: leaderboard
Metric: Ambiguity-aware global multi-label F1 (%) over all questions, on the 100 CVT-Synthetic scenes (rendered CLEVR objects, 5,703 questions; relations left, right, front and behind), asked for the spatial relation between two tagged objects from the source view and from counterfactual viewpoints (yaw rotations and a top view), with the scene given as an image, one scene per request (CVT-Isolated); higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 94.2 | #54 |
| 2 | GPT-5.2 | 80.3 | #105 |
| 3 | Qwen 3.5 Plus (2026-02-15) | 73.3 | #114 |
| 4 | Qwen 3.5 397B A17B | 71.8 | #141 |
| 5 | Kimi K2.5 | 71 | #139 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=cvt-bench-synthetic-isolated-f1 · How It Works · Data refreshed daily, snapshot 2026-10-11.