Wikibench

VideoMME w sub.

multimodal official site →

Multilingual: no

The first-ever comprehensive evaluation benchmark of Multi-modal LLMs in Video analysis. Features 900 videos (254 hours) with 2,700 question-answer pairs covering 6 primary visual domains and 30 subfields. Evaluates temporal understanding across short (11 seconds) to long (1 hour) videos with multi-modal inputs including video frames, subtitles, and audio.

Methodology

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

Leaderboard

Showing 8 of 8 results

  1. Qwen3.6-27B self-reported llm-stats
    87.7%
  2. Qwen3.5-122B-A10B self-reported llm-stats
    87.3%
  3. Qwen3.5-27B self-reported llm-stats
    87.0%
  4. GPT-5 self-reported llm-stats
    86.7%
  5. Qwen3.5-35B-A3B self-reported llm-stats
    86.6%
  6. Qwen2.5 VL 32B Instruct self-reported llm-stats
    77.9%
  7. Qwen2.5-Omni-7B self-reported llm-stats
    72.4%
  8. Qwen2.5 VL 7B Instruct self-reported llm-stats
    71.6%