Multimodal & Grounded benchmark
BabyVision leaderboard
Every model the catalog carries a published BabyVision value for, ranked by that value.
CategoryMultimodal & Grounded
MeasureMultimodal visual reasoning
TasksVisual perception tasks
DifficultyFine-grained visual perception
Published byMuse Spark 1.1 Evaluation Report
A multimodal benchmark for fine-grained visual perception and grounded reasoning tasks.
BabyVision ranking
7 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 |  Qwen3.8 Max | Alibaba | 82.0 |
| 2 |  Muse Spark 1.1 | Meta | 76.3 |
| 3 |  Seed 2.1 Pro | ByteDance | 73.7 |
| 4 | Qwen3.8-27B | Alibaba | 65.7 |
| 5 | Seed 2.1 Turbo | ByteDance | 62.9 |
| 6 |  GLM-5.3-Flash | Z.AI | 53.4 |
| 7 | DSdots3-note Preview | Dots Studio | 50.0 |
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.