Deepscaler
Training environment for DeepScaleR, containing single-turn math problems with rule-based grading
- Domain
- rl-env
- License
- apache-2.0
- Published
- Oct 2025
Cite
Notes
Only stored in your browser.
Top score 80.0% by GPT-4.1 Mini - 2 models reporting (2 frontier)
Score history
2Top models
2
Related tools
1Implementations, trainers, datasets and scaffolds linked to this eval.
FAQ
- What is Deepscaler?
- Training environment for DeepScaleR, containing single-turn math problems with rule-based grading
- What is the current top score on Deepscaler?
- The top reported score is 80.0% by GPT-4.1 Mini, across 2 models reporting (2 from frontier labs).
- How can a model improve its Deepscaler score?
- Tools linked to Deepscaler on Sophon include Deepscaler RL Env (Prime Intellect) - RL environments, datasets, and scaffolds that target this eval.
- What license is Deepscaler under?
- Deepscaler is available under apache-2.0.