HAVEN - Joint Summary Keyframes: leaderboard
Joint summarization on HAVEN (2026), a video understanding benchmark with aligned frames, shots, descriptions and full video documents: the model writes a text summary and selects key frames together, and this board scores the frames by F1 against human-annotated keyframes in percent; higher is better.
Metric: Keyframe selection F1 (%) against human-annotated keyframes when summarizing a video jointly into text and frames (video-to-video-and-text), 15 percent frame budget, zero-shot on a random sample of 100 videos per source dataset; higher is better. Source: arxiv.org. Saturation forecast: Around March 2027. 4 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | VideoLLaMA3-7B | 26.7 | #2064 |
| 2 | Qwen 3 VL 8B Instruct | 23.5 | #1043 |
| 3 | Qwen 2.5 VL 7B Instruct | 17.6 | #1919 |
| 4 | InternVideo2.5-Chat-8B | 6.5 | #2049 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=haven-joint-summary-keyframes · How It Works · Data refreshed daily, snapshot 2026-11-22.