Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Multimodal & Grounded benchmark
Every model the catalog carries a published Video-MME value for, ranked by that value.
A comprehensive benchmark for multimodal large language models on video understanding, covering temporal reasoning, perception, and question answering over videos. 4 models in the ModelChoice catalog have a published value.
Each point is a model with a published Video-MME value and complete token prices, on the 75% input / 25% output blend. Frontier models are spaced evenly along the cost axis.
4 models with a published Video-MME value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Video QA and analysis |
|---|---|---|---|
| 1 | ByteDance | 89.2 | |
| 2 | ByteDance | 89.0 | |
| 3 | Moonshot AI | 87.4 |
What the benchmark measures and how its value is published, from the source’s own record.
Video-MME is a multimodal & grounded benchmark published by Video-MME benchmark. A comprehensive benchmark for multimodal large language models on video understanding, covering temporal reasoning, perception, and question answering over videos. Its evaluation set is described by the source as video understanding. The source rates its difficulty as broad multimodal video reasoning.
Each model's result is published by Video-MME benchmark as video QA and analysis. ModelChoice prints that value to 1 decimal place, exactly as published, and never converts or rescales it. This page ranks the 4 models that carry a published value, highest value first; a model the source never scored is left out rather than ranked at zero. The source does not state whether a higher value is the better result, so neither does this page.
All leaderboards · Multimodal & Grounded capability leaderboard
| 4 | Meituan | 85.2 |
Evidence key: Observed
Rows are ordered by the value Video-MME benchmark published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.