ComBench Shows LLMs Still Lag on Olympiad‑Level Combinatorics Proofs
ComBench introduces 100 human‑annotated Olympiad‑style combinatorics problems, split into analysis‑centric proof grading and construction‑centric verification. Top frontier models hit only 65.4% overall accuracy, highlighting a persistent gap in rigorous reasoning and creative construction. The benchmark gives a clear diagnostic for future model improvements.