Chem Qa
Frontier
Chem-QA: tolerance-scored numeric chemistry problems (SingleTurnEnv)
- Domain
- rl-env
- License
- unknown
- Published
- Oct 2025
Cite
Notes
Only stored in your browser.
Top score 1.01 by GPT-4.1 Mini - 4 models reporting (4 frontier)
Score history
4Top models
4
Related tools
1Implementations, trainers, datasets and scaffolds linked to this eval.
FAQ
- What is Chem Qa?
- Chem-QA: tolerance-scored numeric chemistry problems (SingleTurnEnv)
- What is the current top score on Chem Qa?
- The top reported score is 1.01 by GPT-4.1 Mini, across 4 models reporting (4 from frontier labs).
- How can a model improve its Chem Qa score?
- Tools linked to Chem Qa on Sophon include CHEM QA RL Env (Community) - RL environments, datasets, and scaffolds that target this eval.
- What license is Chem Qa under?
- Chem Qa is available under unknown.