A stricter Video-MME setting that removes subtitle help and tests video understanding from visual and audio context alone.
As of March 2026, Gemini 3 Pro leads the Video-MME (w/o subtitle) leaderboard with 87.7% , followed by GPT-5.2 (85.8%) and Qwen3.6 Plus (84.2%).
Gemini 3 Pro
GPT-5.2
OpenAI
Qwen3.6 Plus
Alibaba
According to BenchLM.ai, Gemini 3 Pro leads the Video-MME (w/o subtitle) benchmark with a score of 87.7%, followed by GPT-5.2 (85.8%) and Qwen3.6 Plus (84.2%). The scores show moderate spread, with meaningful differences between the top tier and mid-tier models.
6 models have been evaluated on Video-MME (w/o subtitle). The benchmark falls in the Multimodal & Grounded category. This category carries a 12% weight in BenchLM.ai's overall scoring system. Video-MME (w/o subtitle) is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
Year
2026
Tasks
Video understanding
Format
Video QA without subtitle context
Difficulty
Multimodal video reasoning
This row isolates raw video understanding by removing subtitle cues. It is a better proxy for whether a model can parse action, scene changes, and temporal context from the media itself.
Qwen3.6 launch benchmarksVersion
Video-MME (w/o subtitle) 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
A stricter Video-MME setting that removes subtitle help and tests video understanding from visual and audio context alone.
Gemini 3 Pro by Google currently leads with a score of 87.7% on Video-MME (w/o subtitle).
6 AI models have been evaluated on Video-MME (w/o subtitle) on BenchLM.
Get notified when new models drop, benchmark scores change, or the leaderboard shifts. One email per week.
Free. No spam. Unsubscribe anytime. We only store derived location metadata for consent routing.