VisualToolBench (VTB)
Full rankings
2 models tested · sorted by score
| # | Model | Score |
|---|---|---|
| 1 | 29.0 | |
| 2 | 27.5 |
Score distribution
Where models cluster
Correlated benchmarks
Pearson r · original research
Frequently asked
About VisualToolBench (VTB)
What does VisualToolBench (VTB) measure?
VisualToolBench (VTB) is a knowledge benchmark in the BenchGecko catalog. 2 AI models have been tested on it. Scores range from 27.5 to 29.0 out of 100.
Which model leads on VisualToolBench (VTB)?
Gemini 3.1 Pro Preview from Google DeepMind leads VisualToolBench (VTB) with a score of 29.0. The median score across 2 tested models is 28.2.
Is VisualToolBench (VTB) saturated?
No · the top score is 29.0 out of 100 (29%). There is still meaningful room for improvement on VisualToolBench (VTB).
What makes VisualToolBench (VTB) distinctive?
VisualToolBench (VTB) is a knowledge benchmark with limited overlap to the rest of the catalog · it measures capabilities that are not well-covered by other benchmarks we track.
How often is VisualToolBench (VTB) data refreshed?
BenchGecko pulls updates daily. New model scores on VisualToolBench (VTB) appear as soon as they are published by Epoch AI or the model provider.
- Category
- Knowledge
- Max score
- 100
- Models
- 2
- Updated
- 2026-04-07
More knowledge benchmarks
Same category · related evaluations