Synthetic Clocks
Environment for evaluating LLMs on synthetic analog clock time reading tasks using image URLs and multiple reward criteria.
- Domain
- rl-env
- License
- unknown
- Published
- Oct 2025
Cite
Notes
Only stored in your browser.
Top score 10.0% by GPT-4.1 - 1 model reporting (1 frontier)
Top models
1
Related tools
1Implementations, trainers, datasets and scaffolds linked to this eval.
FAQ
- What is Synthetic Clocks?
- Environment for evaluating LLMs on synthetic analog clock time reading tasks using image URLs and multiple reward criteria.
- What is the current top score on Synthetic Clocks?
- The top reported score is 10.0% by GPT-4.1, across 1 model reporting (1 from frontier labs).
- How can a model improve its Synthetic Clocks score?
- Tools linked to Synthetic Clocks on Sophon include Synthetic Clocks RL Env (Prime Intellect) - RL environments, datasets, and scaffolds that target this eval.
- What license is Synthetic Clocks under?
- Synthetic Clocks is available under unknown.