CrowdMath: A Dataset of Crowdsourced Mathematical Research Discussions
For researchers evaluating LLMs on mathematical reasoning, this work provides a new benchmark for collaborative open-problem solving, but the gains are incremental as it primarily extends existing evaluation to a new setting.
The authors introduce CrowdMath, a dataset of 164 annotated progress chains from collaborative mathematical research discussions. They benchmark six frontier models, finding they achieve 83-88% accuracy on next-post prediction but only 0.42 macro-F1 on post-role classification, exposing a gap in understanding collaborative mathematical progress.
Large language models have made substantial progress on mathematical reasoning, but existing benchmarks typically evaluate well-specified problems with final answers, step-by-step solutions, or complete proofs. They do not capture collaborative open-problem solving: a setting in which participants propose partial arguments, identify gaps or errors in prior steps, repair flawed reasoning, and gradually synthesize incremental contributions into a proof. We introduce CrowdMath, a dataset of 164 expert-annotated progress chains from the MIT PRIMES--Art of Problem Solving (AoPS) CrowdMath program (2016-2025), a collaborative research initiative whose discussions have led to peer-reviewed publications. Each chain traces a multi-participant forum discussion from an open-problem statement to a completed proof. Posts are labeled by their functional roles in the evolving solution process, including partial progress, proof completion, erroneous reasoning, and error identification. We define evaluation tasks and benchmark six frontier models. Models achieve 83-88% accuracy on next-post prediction, suggesting that they can follow the local flow of mathematical discussion. However, they struggle to identify the functional significance of individual contributions with the best model achieving only 0.42 macro-F1 on post-role classification. CrowdMath exposes a gap between solving well-specified mathematical problems and understanding collaborative mathematical progress as it unfolds.