LongShOTBench - Reasoning: leaderboard
LongShOTBench (arXiv:2512.16978) Reasoning (RE) category breakdown: weighted criterion-level rubric score (0-100%) on temporal, causal, and cross-modal reasoning over long omni-modal videos; higher is better.
Metric: Weighted Rubric Score (%). Source: longshot.cvmbzuai.com. Saturation forecast: Around November 2027. 102 models tracked. Updated 21 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Qwen 3 Omni 30B A3B (Thinking) | 72.44 | ||
| 2 | Gemini 3.1 Pro (Preview) | 65.98 | #99 | |
| 3 | Voxtral-Mini-3B-2507 | 58.37 | #3682 | |
| 4 | Voxtral-Small-24B-2507 | 56.12 | #1246 | |
| 5 | Qwen 3 VL 235B A22B (Thinking) | 54.62 | #459 | |
| 6 | Qwen 3 VL 32B (Thinking) | 52.07 | #573 | |
| 7 | Kimi K2.6 | 51.5 | #192 | |
| 8 | Vero-Qwen3I-8B | 50.6 | ||
| 9 | Nemotron 3 Nano Omni 30B A3B | Reasoning | 50.46 | #1412 |
| 10 | Qwen 3 VL 30B A3B (Thinking) | 50.09 | #719 | |
| 11 | Gemma 3 27B (IT) | 48.36 | #1324 | |
| 12 | Qwen 3 VL 8B (Thinking) | 47.96 | #910 | |
| 13 | Qwen3 Omni 30B A3B Instruct | 47.43 | #930 | |
| 14 | Gemma 3 12B (IT) | 47.02 | #1887 | |
| 15 | Intern-S1-mini | 46.68 | #1178 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=longshotbench-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-21.