LongShOTBench - Medium Videos: leaderboard

LongShOTBench (arXiv:2512.16978) Medium Videos duration slice: weighted criterion-level rubric score (0-100%) on medium-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

#ModelSettingScoreOverall rank
1Qwen 3 Omni 30B A3B (Thinking)63.6
2Gemini 3.1 Pro (Preview)53.09#99
3Voxtral-Mini-3B-250749#3682
4Voxtral-Small-24B-250747.45#1246
5Qwen 3 VL 235B A22B (Thinking)44.81#459
6Qwen 3 VL 32B (Thinking)43.95#573
7Vero-Qwen3I-8B43.84
8Kimi K2.643.54#192
9Qwen 3 VL 30B A3B (Thinking)41.03#719
10Nemotron 3 Nano Omni 30B A3BReasoning40.17#1412
11Qwen 3 VL 235B A22B Instruct39.51#532
12Qwen 3 VL 8B (Thinking)39.29#910
13Intern-S1-mini39.02#1178
14Gemma 3 27B (IT)38.85#1324
15Qwen 3 VL 32B Instruct38.37#606

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=longshotbench-medium-videos · How It Works · Data refreshed daily, snapshot 2026-11-21.