AI Radar
Support
LiveUpdated 2026-11-06 16:05 UTC

TCSExam

TCSExam — 100 research tasks. Four tracks. Machine-verified proofs, solvers and constructions.

TCSExam is 100 research tasks. Four tracks. Machine-verified proofs, solvers and constructions.. It is ranked #1322 on the AI Radar, in Frontier models, first seen 1 days ago and shared in 1 post (1.8k views).

Visit moonshotai.github.io

TCSExam — A benchmark for TCS research Skip to content How far can LLMs advance TCS research? Evaluating large language models across theoretical computer science. From complete proofs and reusable solvers to verified constructions and open conjectures. Results Tasks Paper GitHub Docs Theorem proving Complete proofs, checked by Lean. Solver engineering Reusable programs, tested on hidden instances. Constructions Explicit objects, formally verified properties. Open conjectures Complete resolutions: prove or refute. Task protocols Theorem proving Submit Complete Lean proof Verify Lean kernel + axiom checks 5 Lite / 20 Full tasks Solver…

What people said about TCSExam on X

Kimi发布 TSCExam:理论计算机科学研究任务评测 TCSExam 是由可验证的理论计算机科学研究任务评测模型与 agent 组成的系统。 包含 100 道题;Lite 从 Full 的各类题目中各选取 5 道,共 20 道题。 读法说明:表格列出各套件的题目数量;每道 Solver 题分别提供 Online 和 Offline 两个题目包。 Kimi为了证明 Kimi k3.1 pro的实力,决定自已做评测了。。。。。 这是向 AA 野榜发起的挑战。。。 https://moonshotai.github.io/TCSExam/

— @leo114119, 1 days ago · 13 likes · see the post

Alternatives to TCSExam

TCSExam in numbers

FAQ

What is TCSExam?

100 research tasks. Four tracks. Machine-verified proofs, solvers and constructions. It was first shared on X 1 days ago and is ranked #1322 on the AI Radar.

Is TCSExam free?

Yes, it is free to use.

Who shared TCSExam?

1 account on X, including @leo114119, in 1 post totalling 1.8k views.

Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 65.6k posts from 5k X accounts over the last 14 days, 10.4k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 16:05 UTC. Full method.