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 ZeroBench value for, ranked by that value.
A multi-step visual reasoning benchmark with pass@5 reporting and optional tool use. 11 models in the ModelChoice catalog have a published value.
Each point is a model with a published ZeroBench value and complete token prices, on the 75% input / 25% output blend. Frontier models are spaced evenly along the cost axis.
11 models with a published ZeroBench 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 | Multi-step visual reasoning |
|---|---|---|---|
| 1 | Meta | 50.0 | |
| 2 | OpenAI | 41.0 | |
| 3 | Moonshot AI | 39.0 | |
What the benchmark measures and how its value is published, from the source’s own record.
ZeroBench is a multimodal & grounded benchmark published by Muse Spark Eval Methodology. A multi-step visual reasoning benchmark with pass@5 reporting and optional tool use. Its evaluation set is described by the source as 100 visual reasoning questions. The source rates its difficulty as tool-augmented visual reasoning.
Each model's result is published by Muse Spark Eval Methodology as multi-step visual reasoning. ModelChoice prints that value to 1 decimal place, exactly as published, and never converts or rescales it. This page ranks the 11 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 |
| Meta |
| 33.0 |
| 5 | 29.0 |
| 6 | Alibaba | 24.0 |
| 7 | Moonshot AI | 23.0 |
| 8 | DSdots3-note Preview | Dots Studio | 19.0 |
| 9 | ByteDance | 18.0 |
| 10 | TMInkling 2 Mini | Thinking Machines Lab | 17.0 |
| 11 | ByteDance | 11.0 |
Evidence key: Observed
Rows are ordered by the value Muse Spark Eval Methodology 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.