MulSeT
Multi-Category eval and train data for images
- Domain
- rl-env
- License
- unknown
- Published
- Oct 2025
Cite
Notes
Only stored in your browser.
Top score 70.0% by Gemini 2.5 Pro - 7 models reporting (1 frontier)
Score history
2Top models
7
Related tools
1Implementations, trainers, datasets and scaffolds linked to this eval.
FAQ
- What is MulSeT?
- Multi-Category eval and train data for images
- What is the current top score on MulSeT?
- The top reported score is 70.0% by Gemini 2.5 Pro, across 7 models reporting (1 from frontier labs).
- How can a model improve its MulSeT score?
- Tools linked to MulSeT on Sophon include Mulset RL Env (Community) - RL environments, datasets, and scaffolds that target this eval.
- What license is MulSeT under?
- MulSeT is available under unknown.