Alphabet Sort
This task requires the model to maintain and update an alphabetically sorted list of names across multiple conversation turns.
- Domain
- rl-env
- License
- apache-2.0
- Published
- Aug 2025
Cite
Notes
Only stored in your browser.
Top score 0.0% by Claude Sonnet 4.5 - 1 model reporting (1 frontier)
Top models
1
Related tools
1Implementations, trainers, datasets and scaffolds linked to this eval.
FAQ
- What is Alphabet Sort?
- This task requires the model to maintain and update an alphabetically sorted list of names across multiple conversation turns.
- What is the current top score on Alphabet Sort?
- The top reported score is 0.0% by Claude Sonnet 4.5, across 1 model reporting (1 from frontier labs).
- How can a model improve its Alphabet Sort score?
- Tools linked to Alphabet Sort on Sophon include Alphabet SORT RL Env (Community) - RL environments, datasets, and scaffolds that target this eval.
- What license is Alphabet Sort under?
- Alphabet Sort is available under apache-2.0.