LongShOTBench - Multimodal: leaderboard
LongShOTBench (arXiv:2512.16978) Multimodal (MM) category breakdown: weighted criterion-level rubric score (0-100%) on questions requiring joint visual, audio, and speech integration over long videos; higher is better.
Metric: Weighted Rubric Score (%). Source: longshot.cvmbzuai.com. Saturation forecast: Around September 2028. 102 models tracked. Updated 21 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3 Omni 30B A3B (Thinking) | 66.97 | |
| 2 | Gemini 3.1 Pro (Preview) | 59.63 | #99 |
| 3 | Qwen 3 VL 32B (Thinking) | 49.72 | #573 |
| 4 | Vero-Qwen3I-8B | 49.27 | |
| 5 | Qwen 3 VL 235B A22B (Thinking) | 48.56 | #459 |
| 6 | Voxtral-Small-24B-2507 | 48.54 | #1246 |
| 7 | Voxtral-Mini-3B-2507 | 47.23 | #3682 |
| 8 | Kimi K2.6 | 46.83 | #192 |
| 9 | Qwen 3 VL 235B A22B Instruct | 46.01 | #532 |
| 10 | Qwen 3 VL 30B A3B (Thinking) | 45.87 | #719 |
| 11 | Qwen 3 VL 8B (Thinking) | 45.34 | #910 |
| 12 | Qwen 3 VL 32B Instruct | 44.34 | #606 |
| 13 | Intern-S1-mini | 44.28 | #1178 |
| 14 | Gemma 3 27B (IT) | 43.56 | #1324 |
| 15 | Gemma 3 12B (IT) | 42.07 | #1887 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=longshotbench-multimodal · How It Works · Data refreshed daily, snapshot 2026-11-21.