31B (fine-tune of Qwen3-30B-A3B-Thinking-2507; MoE)
Apache 2.0
Specialized mathematical reasoning model for problem-solving and proof-writing in natural language; developed in collaboration with Hillclimb AI; scores 87/120 on Putnam 2025 (base model only achieves 24/120 - 3.6x improvement); designed to work with Nomos Reasoning Harness (open-sourced concurrently); significant advancement in domain-specific mathematical capabilities; demonstrates power of targeted fine-tuning for specialized reasoning tasks; recommended for use without system prompts.