CapRiCorn-1K-V - Referential Consistency: leaderboard
Subject referential consistency of visual-only captions on the 1,000 CapRiCorn-1K videos (Chen et al., 2026): the share of pairs of descriptions of the same subject that a GPT-4.1 judge groups as one referent, in percent; higher is better.
Metric: Subject referential consistency (%; share of same-subject description pairs a GPT-4.1 judge clusters as one referent, over all pairs of that subject's vision-only keypoints, 1,000 videos). Source: arxiv.org. Saturation forecast: Around 2029. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3.5 9B | 3.1 | #803 |
| 2 | Qwen 3.6 27B | 3.1 | #339 |
| 3 | Qwen 3.6 35B A3B | 2.9 | #461 |
| 4 | Qwen 3.5 122B A10B | 2.6 | #329 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=capricorn-1k-v-referential-consistency · How It Works · Data refreshed daily, snapshot 2026-11-12.