Medqa Followup
Multi-turn robustness evaluation for medical LLMs - tests whether models maintain correct answers when challenged with follow-up interventions
- Domain
- rl-env
- License
- unknown
- Published
- Dec 2025
Cite
Notes
Only stored in your browser.
Top score 10.8% by GPT-4o - 2 models reporting (2 frontier)
Score history
2Top models
2
Related tools
1Implementations, trainers, datasets and scaffolds linked to this eval.
FAQ
- What is Medqa Followup?
- Multi-turn robustness evaluation for medical LLMs - tests whether models maintain correct answers when challenged with follow-up interventions
- What is the current top score on Medqa Followup?
- The top reported score is 10.8% by GPT-4o, across 2 models reporting (2 from frontier labs).
- How can a model improve its Medqa Followup score?
- Tools linked to Medqa Followup on Sophon include Medqa Followup RL Env (Community) - RL environments, datasets, and scaffolds that target this eval.
- What license is Medqa Followup under?
- Medqa Followup is available under unknown.