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
MMMU-Pro with Python. Every model the catalog carries a published MMMU-Pro w/ Python value for, ranked by that value.
Tool-augmented MMMU-Pro variant that allows Python assistance during multimodal reasoning. 10 models in the ModelScale catalog have a published value.
Each point is a model with a published MMMU-Pro w/ Python value and complete token prices, on the 75% input / 25% output blend. Frontier models are spaced evenly along the cost axis.
10 models with a published MMMU-Pro w/ Python 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 | Image + text question answering with Python |
|---|---|---|---|
| 1 | Moonshot AI | 90 | |
| 2 | OpenAI | 84.6 | |
| 3 | Moonshot AI | 83.4 |
What the benchmark measures and how its value is published, from the source’s own record.
MMMU-Pro w/ Python (MMMU-Pro with Python) is a multimodal & grounded benchmark published by Introducing GPT-5.4 mini and nano. Tool-augmented MMMU-Pro variant that allows Python assistance during multimodal reasoning. Its evaluation set is described by the source as multimodal academic reasoning. The source rates its difficulty as frontier multimodal.
Each model's result is published by Introducing GPT-5.4 mini and nano as image + text question answering with Python. ModelScale prints that value exactly as published, and never converts or rescales it. This page ranks the 10 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 | OpenAI | 83.2 |
| 5 | OpenAI | 82.1 |
| 6 | OpenAI | 82 |
| 7 | Moonshot AI | 80.1 |
| 8 | OpenAI | 79.5 |
| 9 | OpenAI | 78 |
| 10 | OpenAI | 69.5 |
Evidence key: Observed
Rows are ordered by the value Introducing GPT-5.4 mini and nano 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.