Mnist Adversarial
Frontier
Distinguishing adversarial examples from normal MNIST digits and identifying the digit class.
- Domain
- rl-env
- License
- unknown
- Published
- Aug 2025
Cite
Notes
Only stored in your browser.
Top score 54.5% by GPT-4.1 Mini - 3 models reporting (3 frontier)
Score history
3Top models
3
Related tools
1Implementations, trainers, datasets and scaffolds linked to this eval.
FAQ
- What is Mnist Adversarial?
- Distinguishing adversarial examples from normal MNIST digits and identifying the digit class.
- What is the current top score on Mnist Adversarial?
- The top reported score is 54.5% by GPT-4.1 Mini, across 3 models reporting (3 from frontier labs).
- How can a model improve its Mnist Adversarial score?
- Tools linked to Mnist Adversarial on Sophon include Mnist Adversarial RL Env (Community) - RL environments, datasets, and scaffolds that target this eval.
- What license is Mnist Adversarial under?
- Mnist Adversarial is available under unknown.