Xbench Scienceqa
A science question answering environment for evaluating scientific reasoning and problem-solving capabilities.
- Domain
- rl-env
- License
- unknown
- Published
- Nov 2025
Cite
Notes
Only stored in your browser.
Top score 53.3% by Gemini 2.5 Pro - 5 models reporting (2 frontier)
Score history
3Top models
5
Related tools
1Implementations, trainers, datasets and scaffolds linked to this eval.
FAQ
- What is Xbench Scienceqa?
- A science question answering environment for evaluating scientific reasoning and problem-solving capabilities.
- What is the current top score on Xbench Scienceqa?
- The top reported score is 53.3% by Gemini 2.5 Pro, across 5 models reporting (2 from frontier labs).
- How can a model improve its Xbench Scienceqa score?
- Tools linked to Xbench Scienceqa on Sophon include Xbench Scienceqa RL Env (Community) - RL environments, datasets, and scaffolds that target this eval.
- What license is Xbench Scienceqa under?
- Xbench Scienceqa is available under unknown.