MathAdv Benchmark

What is MathAdv?

Evaluates theorem proving and auxiliary tasks including multiple-choice, fill-in-the-blank, and reformulation robustness across 13 mathematical domains.

Released

2026-08-26

Evaluates

General AI, Language & Knowledge, Mathematics & Formal Science, cs.CL

Openness

unknown

Importer

Claire Radar

Review status

ai-reviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2608.25449

MathAdv paper and code

• Paper https://arxiv.org/abs/2608.25449
• Code https://github.com/margotyjx/MathAdv.git

Which sources cite MathAdv?

• MathAdv

Related General AI, Language & Knowledge, Mathematics & Formal Science, cs.CL benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• A3S-Bench
• AARRI-Bench
• ABC-Bench
• ActBench