PutnamBench

Link to the repository on GitHub: https://github.com/trishullab/PUTNAM PutnamBench PutnamBench is a benchmark for the evaluation of theorem-proving algorithms on competition mathematics problems sourced from the William Lowell Putnam Mathematical Competition years 1965 - 2023. Our formalizations currently support three

Papers using PutnamBench (4)

STP: Self-play LLM Theorem Provers with Iterative Conjecturing and Proving2025DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decomposition2025GDEPO: Group Dual-dynamic and Equal-right Advantage Policy Optimization with Enhanced Training Data Utilization for Sample-Constrained Reinforcement Learning2026Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction2025