PrimeIntellect/INTELLECT-MATH
PrimeIntellect/INTELLECT-MATH is a 7.6 billion parameter model developed by PrimeIntellect, specifically optimized for advanced mathematical reasoning tasks. This model was trained using a two-stage process involving supervised fine-tuning (SFT) on verified QwQ outputs and reinforcement learning (RL) with the PRIME-RL recipe. It demonstrates superior performance on mathematical benchmarks like MATH-500 and OLYMPIADBENCH, outperforming previous state-of-the-art models in mathematical problem-solving.
Loading preview...
INTELLECT-MATH: Advanced Mathematical Reasoning
INTELLECT-MATH is a 7.6 billion parameter language model developed by PrimeIntellect, engineered for frontier mathematical reasoning. It leverages a unique two-stage training approach to achieve its specialized capabilities.
Key Capabilities & Training:
- Optimized for Math: Specifically designed and trained to excel in complex mathematical problem-solving.
- Two-Stage Training: Utilizes an initial Supervised Fine-Tuning (SFT) stage on high-quality, verified QwQ outputs, followed by a Reinforcement Learning (RL) stage using the PRIME-RL recipe.
- Efficient RL: Achieves performance comparable to previous state-of-the-art models like Eurus-2-PRIME with 10x faster RL training, attributed to its superior synthetic SFT dataset.
Performance Highlights:
INTELLECT-MATH demonstrates strong performance across various mathematical benchmarks, often surpassing other models in its class:
- MATH-500: Achieves 82.0% accuracy.
- OLYMPIADBENCH: Scores 49.5%.
- AIME 2024: Reaches 26.7%.
- AMC: Attains 60.2%.
- MINERVA MATH: Scores 39.7%.
Use Cases:
This model is ideal for applications requiring robust mathematical reasoning, problem-solving, and complex calculation capabilities, particularly in competitive math or scientific domains.