清华与 Moonshot AI 提出 TCSExam 基准：GPT-6 Astra 定理证明率达 70.0%
清华和 Moonshot AI 搞了个 TCSExam 测试集，GPT-6 Astra 证定理能拿 70.0%，但 30 个开放猜想全挂，差距很直观。
清华大学与 Moonshot AI 发布 TCSExam 基准，包含 100 道专家审核任务，覆盖 Lean 定理证明、求解器工程、纪录构造和 30 个理论计算机科学开放猜想四个方向，所有提交由 Lean 内核或任务检查器验证。在无提示引理的条件下，GPT-6 Astra 定理证明成功率为 70.0%，Kimi K3.1 Pro 为 38.3%，其余 6 个智能体均不超过 11.7%。但在 30 个开放猜想上，GPT-6 Astra 一个都未能解决，仅有的几次被接受的提交改编自 OpenAI 已公开的反例与证明。
New Tsinghua and Moonshot AI paper finds that GPT-6 Astra proves 70.0% of research-level computer science theorems in Lean, yet the same model resolves 0 of 30 open conjectures in theoretical computer science (TCS).
Theoretical computer science is a natural test for AI research, because proofs can be machine-checked and records can be beaten. Existing benchmarks cover only slices, like proofs or code.
TCSExam has 100 expert-reviewed tasks in 4 tracks: Lean theorem proving, solver engineering, record-setting constructions, and 30 open conjectures. The Lean kernel or a task checker verifies every submission.
Without supplied lemmas, GPT-6 Astra fully proved theorems in 70.0% of attempts, Kimi K3.1 Pro in 38.3%, and the other 6 agents in at most 11.7%. The few accepted conjecture submissions adapted counterexamples and proofs OpenAI had already published.
