# AdvancedMathBench: A Benchmark Suite for Advanced Mathematical Proof Generation and Verification

Source: [arXiv](https://arxiv.org/abs/2607.11849v1)  
Feed7 permalink: https://feed7.dev/p/2607-11849v1-1sjdl4n  
Published: Unknown  
Trust: Needs Review (needs_review)

## Why Included

AdvancedMathBench separates proof writing from verification and finds frontier models especially weak at rejecting invalid proofs, a warning against trusting agent self-review on rigorous reasoning.

## Source Summary

AdvancedMathBench separates construction from checking: **ProverBench has 296 problems** from undergraduate through doctoral qualifying-exam level, while **VerifierBench has 888 generated proof trajectories** with expert ground truth.

## Practical Implication

For reasoning-heavy agents, evaluate generation and verification independently. The best reported proof scores were **75.8 on UGD and 66.1 on QE**, so adding a verifier does not by itself establish correctness.

## Agent-Ready Context

AdvancedMathBench separates construction from checking: **ProverBench has 296 problems** from undergraduate through doctoral qualifying-exam level, while **VerifierBench has 888 generated proof trajectories** with expert ground truth.

For reasoning-heavy agents, evaluate generation and verification independently. The best reported proof scores were **75.8 on UGD and 66.1 on QE**, so adding a verifier does not by itself establish correctness.

The best verifier reached only **65.1 Balanced F1**, and models generally had low true-negative rates. The benchmark targets advanced mathematics, so its results do not directly measure coding-agent review.

## Context Map

- Layer: benchmark
- Domains: research
- Topics: reasoning, agent-evals, agent-reliability

## Uncertainty

- The best verifier reached only **65.1 Balanced F1**, and models generally had low true-negative rates. The benchmark targets advanced mathematics, so its results do not directly measure coding-agent review.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.