OmniCap-IF: leaderboard
Metric: Overall constraint satisfaction rate (CSR, %): share of all constraints satisfied, on multi-constraint captioning instructions on videos with sound; format constraints are checked by rule-based tools on LLM-extracted structure, content constraints by temporal-IoU tools or a gpt-5-mini judge answering binary and multiple-choice questions against the caption; higher is better. Source: arxiv.org. Saturation forecast: Around December 2026. 14 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 80.65 |
| 2 | Gemini 3 Flash | 79.5 |
| 3 | MiMo-V2.5 | 76.22 |
| 4 | MiMo-V2-Omni | 74.4 |
| 5 | MiniCPM-o-4.5 | 64.69 |
| 6 | Qwen3 Omni 30B A3B Instruct | 62.65 |
| 7 | Qwen2.5-Omni-7B | 49.19 |
Interactive version: theaggregate.ai/benchmark?slug=omnicap-if · How It Works · Data refreshed daily, snapshot 2026-09-29.