LongShOTBench - Short Videos: leaderboard
LongShOTBench (arXiv:2512.16978) Short Videos duration slice: weighted criterion-level rubric score (0-100%) on short-duration omni-modal videos; higher is better.
Metric: Weighted Rubric Score (%). Source: longshot.cvmbzuai.com. Saturation forecast: Around 2029. 102 models tracked. Updated 21 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Qwen 3 Omni 30B A3B (Thinking) | 58.05 | ||
| 2 | Gemini 3.1 Pro (Preview) | 48.53 | #99 | |
| 3 | Qwen 3 VL 235B A22B Instruct | 43.47 | #532 | |
| 4 | Vero-Qwen3I-8B | 42.57 | ||
| 5 | Qwen 3 VL 235B A22B (Thinking) | 42.56 | #459 | |
| 6 | Voxtral-Mini-3B-2507 | 42.26 | #3682 | |
| 7 | Voxtral-Small-24B-2507 | 42.13 | #1246 | |
| 8 | Qwen 3 VL 32B (Thinking) | 41.73 | #573 | |
| 9 | Nemotron 3 Nano Omni 30B A3B | Reasoning | 40.76 | #1412 |
| 10 | Qwen 3 VL 32B Instruct | 40.23 | #606 | |
| 11 | Qwen 3 VL 8B (Thinking) | 40.08 | #910 | |
| 12 | Kimi K2.6 | 39.97 | #192 | |
| 13 | Gemma 3 27B (IT) | 38.26 | #1324 | |
| 14 | Qwen 3 VL 30B A3B (Thinking) | 36.49 | #719 | |
| 15 | Gemma 4 31B (IT) | 36.38 | #350 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=longshotbench-short-videos · How It Works · Data refreshed daily, snapshot 2026-11-21.