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 BabyVision value for, ranked by that value.
A multimodal benchmark for fine-grained visual perception and grounded reasoning tasks. 12 models in the ModelChoice catalog have a published value.
Each point is a model with a published BabyVision value and complete token prices, on the 75% input / 25% output blend. Frontier models are spaced evenly along the cost axis.
12 models with a published BabyVision 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 | Multimodal visual reasoning |
|---|---|---|---|
| 1 | Alibaba | 82.0 | |
| 2 | Meta | 80.2 | |
| 3 | Meta | 76.3 |
What the benchmark measures and how its value is published, from the source’s own record.
BabyVision is a multimodal & grounded benchmark published by Muse Spark 1.1 Evaluation Report. A multimodal benchmark for fine-grained visual perception and grounded reasoning tasks. Its evaluation set is described by the source as visual perception tasks. The source rates its difficulty as fine-grained visual perception.
Each model's result is published by Muse Spark 1.1 Evaluation Report as multimodal visual reasoning. ModelChoice prints that value to 1 decimal place, exactly as published, and never converts or rescales it. This page ranks the 12 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 | ByteDance | 73.7 |
| 5 | TMInkling 2 Small | Thinking Machines Lab | 68.6 |
| 6 | Alibaba | 65.7 |
| 7 | ByteDance | 62.9 |
| 8 | Z.AI | 53.4 |
| 8 | TMInkling 2 Mini | Thinking Machines Lab | 53.4 |
| 10 | DSdots3-note Preview | Dots Studio | 50.0 |
| 11 | NVIDIA | 29.6 |
| 12 | NVIDIA | 29.5 |
Evidence key: Observed
Rows are ordered by the value Muse Spark 1.1 Evaluation Report 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.