Seeclick
Test model's ability to correctly click on target UI
- Domain
- rl-env
- License
- unknown
- Published
- Oct 2025
Cite
Notes
Only stored in your browser.
Top score 20.0% by GPT-4.1 Mini - 1 model reporting (1 frontier)
Top models
1
Related tools
1Implementations, trainers, datasets and scaffolds linked to this eval.
FAQ
- What is Seeclick?
- Test model's ability to correctly click on target UI
- What is the current top score on Seeclick?
- The top reported score is 20.0% by GPT-4.1 Mini, across 1 model reporting (1 from frontier labs).
- How can a model improve its Seeclick score?
- Tools linked to Seeclick on Sophon include Seeclick RL Env (Prime Intellect) - RL environments, datasets, and scaffolds that target this eval.
- What license is Seeclick under?
- Seeclick is available under unknown.