CapRiCorn-1K: leaderboard
Metric: Keypoint accuracy (%; share of annotated keypoints a GPT-4.1 judge marks correctly mentioned in the audiovisual caption, 1,000 videos of 15 s to 10 min). Source: arxiv.org. Saturation forecast: Around January 2027. 18 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 42.5 |
| 2 | Gemini 3 Flash | 41.5 |
| 3 | Qwen3 Omni 30B A3B Instruct | 10.3 |
| 4 | Qwen2.5-Omni-7B | 5.1 |
Interactive version: theaggregate.ai/benchmark?slug=capricorn-1k · How It Works · Data refreshed daily, snapshot 2026-09-26.