Skip to content

Video-MME without subtitle

A stricter Video-MME setting that removes subtitle help and tests video understanding from visual and audio context alone.

7 models

Higher is better.

  1. 1Gemini 3 ProGoogle87.7
  2. 2GPT-5.2OpenAI85.8
  3. 3Qwen3.5 397BAlibaba83.7
  4. 4Kimi K2.5Moonshot AI83.2
  5. 5Qwen3.6-35B-A3BAlibaba82.5
  6. 6Claude Opus 4.5Anthropic81.4
  7. 7Nemotron 3 Nano Omni 30B A3BNVIDIA72.2
Higher is better. Bar colour: blue proprietary, orange open weights, green other.

About this benchmark

Metric
Video QA without subtitle context
Tasks
Video understanding
Authors
Qwen (2026)

Scores are as reported by model developers or evaluators and may use different settings (for example reasoning effort or tools). Compare with care.