sarahmart / HARDMathLinks
A new dataset of difficult graduate-level applied mathematics problems; evaluations demonstrate that leading LLMs currently exhibit low accuracy in solving these problems.
☆19Updated 3 months ago
Alternatives and similar repositories for HARDMath
Users that are interested in HARDMath are comparing it to the libraries listed below
Sorting:
- [AAAI 2025 oral] Evaluating Mathematical Reasoning Beyond Accuracy☆61Updated 5 months ago
- The rule-based evaluation subset and code implementation of Omni-MATH☆22Updated 5 months ago
- Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision☆120Updated 8 months ago
- The official repository of the Omni-MATH benchmark.☆83Updated 5 months ago
- Revisiting Mid-training in the Era of RL Scaling☆48Updated last month
- GSM-Plus: Data, Code, and Evaluation for Enhancing Robust Mathematical Reasoning in Math Word Problems.☆62Updated 10 months ago
- ☆13Updated 10 months ago
- GenRM-CoT: Data release for verification rationales☆61Updated 7 months ago
- A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models☆55Updated 3 months ago
- [ICML 2025] Teaching Language Models to Critique via Reinforcement Learning☆98Updated last month
- [NeurIPS'24] Official code for *🎯DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving*☆106Updated 5 months ago
- ☆69Updated 6 months ago
- The code for creating the iGSM datasets in papers "Physics of Language Models Part 2.1, Grade-School Math and the Hidden Reasoning Proces…☆54Updated 4 months ago
- Collections of RLxLM experiments using minimal codes☆13Updated 3 months ago
- Test-time-training on nearest neighbors for large language models☆41Updated last year
- The code of “Improving Weak-to-Strong Generalization with Scalable Oversight and Ensemble Learning”☆16Updated last year