Video-MME without subtitle (Video-MME (w/o subtitle))
We show this table for reference; we do not rank on it.
A stricter Video-MME setting that removes subtitle help and tests video understanding from visual and audio context alone.
Benchmark score on Video-MME (w/o subtitle) — November 13, 2026
We compile the Video-MME (w/o subtitle) rows from provider self-reports and secondary reports. Gemini 3 Pro leads the table at 87.7%, followed by GPT-5.2 (85.8%) and Qwen3.5 397B (83.7%). We do not use these results to rank models overall.
Gemini 3 Pro
GPT-5.2
OpenAI
Another lab’s comparison tableQwen3.5 397B
Alibaba
Reported by Alibaba8 modelsMultimodal & GroundedCurrentDisplay onlyUpdated November 13, 2026
Benchmark score table (8 models)
None of the 8 results on this page has a documented run by the benchmark or an independent evaluator: 4 reported by the labs that built the models and 4 reported in another publisher’s document.
| Rank | Model / configuration | Score | Who ran it | Parameters (B) | Open / closed |
|---|---|---|---|---|---|
| 1 | Gemini 3 ProGoogleAnother lab’s comparison table | 87.7% | Another lab’s comparison table | Not reported | Closed |
| 2 | GPT-5.2OpenAIAnother lab’s comparison table | 85.8% | Another lab’s comparison table | Not reported | Closed |
| 3 | Qwen3.5 397BAlibabaReported by Alibaba | 83.7% | Reported by Alibaba | Not reported | Open |
| 4 | Kimi K2.5Moonshot AIAnother lab’s comparison table | 83.2% | Another lab’s comparison table | Not reported | Open |
| 5 | Qwen3.6-35B-A3BAlibabaReported by Alibaba | 82.5% | Reported by Alibaba | Not reported | Open |
| 6 | Claude Opus 4.5AnthropicAnother lab’s comparison table | 81.4% | Another lab’s comparison table | Not reported | Closed |
| 7 | Nemotron 3 Nano Omni 30B A3BNVIDIAReported by NVIDIA | 72.2% | Reported by NVIDIA | Not reported | Open |
| 8 | LFM3-VL-2BLiquidAIReported by LiquidAI | 62.8% | Reported by LiquidAI | Not reported | Open |
- Lab-reported
- Benchmark-run
- Independent
Results reported by model developersUnranked
Labs ran these themselves, with a metric, split or setting the table above does not use. They take no rank here.
| Model | Reported value | What was measured | Against the table above | Who ran it |
|---|---|---|---|---|
| Gemini Decision 1Google | 69.1%Top-1 accuracy | Video-MMENo subtitles | Same measure as the scores above, run by the lab | Reported by Google |
A lab’s own result is shown for reference. It never takes a rank on this board.
How we label sourcesAmong the reported Video-MME (w/o subtitle) rows, Gemini 3 Pro is first at 87.7%. The third row is 4.0 points behind. The broader top-10 range is 24.9 points, so the table still separates the published systems.
8 models have been evaluated on Video-MME (w/o subtitle). The benchmark falls in the Multimodal & Grounded category. Video-MME (w/o subtitle) is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
About 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.
Freshness and 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.
Questions
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)?
Gemini 3 Pro by Google currently leads with a score of 87.7% on Video-MME (w/o subtitle).
How many models are evaluated on Video-MME (w/o subtitle)?
8 AI models have published results on Video-MME (w/o subtitle) in the BenchLM catalog.
Compare top models on Video-MME (w/o subtitle)
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 7,000+ subscribers.
One email each week. Unsubscribe anytime.