# Ramanujan Challenge Results: AI-Assisted Evaluation Pipeline for Multi-Format Proofs

**Authors:** Alan Sorani, Ashvni Narayanan, Michael Shalyt, Tali Monderer, Rotem Kalisch, Hila Barkan, Elyasheev Leibtag, Shachar Weinbaum, Carsten Schneider, John Campbell, Ido Kaminer  
**Lab:** Technion – Israel Institute of Technology · **Published:** 29 Oct 2026  
**Links:** [arXiv](https://arxiv.org/abs/2610.40551) · [PDF](https://arxiv.org/pdf/2610.40551) · [This page](https://omen-bit.github.io/ai-paper-daily/paper/2610.40551.html)

## Key numbers

- **23% → 6%**: …reduces false-positive verdicts on natural language proofs from 23% to 6% and improves judgment accuracy on…
- **46% → 58%**: …proofs from 23% to 6% and improves judgment accuracy on supporting code from 46% to 58%.

## Abstract

As AI's mathematical capabilities rapidly improve, meaningful benchmarks are shifting from university-level problems and math olympiads to research-level mathematics. The Ramanujan Challenge is a benchmark comprised of research-level problems in number theory, including unpublished results and open conjectures. It presented concrete formulas for mathematical constants whose correctness can be checked numerically, while their proofs may require non-obvious mathematics. Here, we analyze the Challenge submissions, measuring the relative success of different AI models, Computer Algebra Systems (CAS), and formal tools. We find correct submissions that are conceptually distinct from the official solutions, and a proof of one of the published open conjectures. Evaluating the submissions exposed a second challenge: judging complex proofs reliably at scale. We introduce an AI-assisted evaluation pipeline for natural language proofs, CAS code, and Lean formalizations that assesses semantic and logical correctness. Compared with the conventional one-shot LLM judgment, our pipeline reduces false-positive verdicts on natural language proofs from 23% to 6% and improves judgment accuracy on supporting code from 46% to 58%. This approach provides a methodology for evaluating research-level mathematics at scale, with potential applications across mathematics and AI for science.

---

Notes written by AI from the paper, numbers copied from the abstract. Check the paper before you rely on them. From AI Papers Daily.