Benchmark RadarAI BENCHMARK PROFILE
GTBench
GTBench is a curriculum-grounded benchmark for evaluating LLMs as mathematical research assistants in graph theory, with problems across three difficulty groups.
- Released
- 2026-06-02
- Readiness
- Paper only
- Primary field
- General AI
Why it matters
It reveals performance gaps in graph-theoretic reasoning among frontier models, informing the use of AI in education and research.
Motivation
Large language models (LLMs) are increasingly used as self-study assistants in technical disciplines, yet their reliability as mathematical reasoning assistants remains poorly understood.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.