Wikibench

MMVU

reasoning

Multilingual: no

MMVU (Multimodal Multi-disciplinary Video Understanding) is a benchmark for evaluating multimodal models on video understanding tasks across multiple disciplines, testing comprehension and reasoning capabilities on video content.

Methodology

Imported from llm-stats public benchmark metadata. Modality: multimodal. Max score: 1. Categories: multimodal, reasoning, video, vision. Language: en. Verified by llm-stats: no.

Leaderboard

Showing 4 of 4 results

  1. Kimi K2.5 self-reported llm-stats
    80.4%
  2. Qwen3.5-122B-A10B self-reported llm-stats
    74.7%
  3. Qwen3.5-27B self-reported llm-stats
    73.3%
  4. Qwen3.5-35B-A3B self-reported llm-stats
    72.3%