Multimodal & Grounded benchmark
CountBench leaderboard
Every model the catalog carries a published CountBench value for, ranked by that value.
CategoryMultimodal & Grounded
MeasureImage-grounded counting
TasksVisual counting tasks
DifficultyFine-grained visual perception
Published byQwen3.6 launch benchmarks
A visual counting benchmark that tests whether a model can count objects and entities reliably in complex scenes.
CountBench ranking
4 models with a published CountBench 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-grounded counting |
|---|---|---|---|
| 1 |  Qwen3.6-27B | Alibaba | 97.8 |
| 2 | ZYZAYA1-VL-8B | Zyphra | 88.1 |
| 3 |  LFM2.5-VL-3B | LiquidAI | 87.3 |
| 4 | LFM2.5-VL-450M | LiquidAI | 73.3 |
Evidence key: Observed
Rows are ordered by the value Qwen3.6 launch benchmarks 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.