Multimodal · Benchmark profile
A stricter Video-MME setting that removes subtitle help and tests video understanding from visual and audio context alone.
Data verified 27 Jul 2026 · Methodology 1.8.0
Benchmark score on Video-MME without subtitle
Qwen3.6-35B-A3B leads at 82.5%, followed by Nemotron 3 Nano Omni 30B A3B (72.2%).
2 ranked models · higher is better · labels show rank and score
| Model | Rank | Provider | Score |
|---|---|---|---|
| Qwen3.6-35B-A3B | #1 | Alibaba Cloud | 82.5% |
| Nemotron 3 Nano Omni 30B A3B | #2 | NVIDIA | 72.2% |
One best score per model · higher is better
| Rank | Model | Provider | License | Evidence use | Score |
|---|---|---|---|---|---|
| #1 | Qwen3.6-35B-A3B qwen3-6-35b-a3b | Alibaba Cloud | open | Estimated reference | 82.5% |
| #2 | Nemotron 3 Nano Omni 30B A3B nemotron-3-nano-omni-30b-a3b | NVIDIA | open | Estimated reference | 72.2% |
About Video-MME without subtitle
A stricter Video-MME setting that removes subtitle help and tests video understanding from visual and audio context alone. Results stay tied to the exact model variant and evaluation system. Multiple systems for the same model use the best published score on this page; overall Lumina scoring uses the median of ranking-eligible rows.
Open benchmark source ↗FAQ
A stricter Video-MME setting that removes subtitle help and tests video understanding from visual and audio context alone.
Qwen3.6-35B-A3B by Alibaba Cloud currently leads with 82.5%.
2 models in the LuminaBench cohort have a qualifying score on this benchmark.
Related
