Benchmark profile
Video-MME without subtitle (Video-MME (w/o subtitle))
A stricter Video-MME setting that removes subtitle help and tests video understanding from visual and audio context alone.
Data verifiedBenchmark score on Video-MME (w/o subtitle) — July 23, 2026
BenchLM mirrors the published score view for Video-MME (w/o subtitle). Qwen3.6-35B-A3B leads the public snapshot at 82.5% , followed by Nemotron 3 Nano Omni 30B A3B (72.2%). BenchLM does not use these results to rank models overall.
Qwen3.6-35B-A3B
Alibaba
qwen3-6-35b-a3b
Nemotron 3 Nano Omni 30B A3B
NVIDIA
nemotron-3-nano-omni-30b-a3b
Benchmark score table (2 models)
ScoreAbout Video-MME (w/o subtitle)
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.
BenchLM freshness & provenance
Version
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.
FAQ
What does Video-MME (w/o subtitle) measure?
A stricter Video-MME setting that removes subtitle help and tests video understanding from visual and audio context alone.
Which model scores highest on Video-MME (w/o subtitle)?
Qwen3.6-35B-A3B by Alibaba currently leads with a score of 82.5% on Video-MME (w/o subtitle).
How many models are evaluated on Video-MME (w/o subtitle)?
2 AI models have been evaluated on Video-MME (w/o subtitle) on BenchLM.
Compare Top Models on Video-MME (w/o subtitle)
Choose a model with this week’s evidence
Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.
One email each week. Unsubscribe anytime.