@Kimi_Moonshot open-sourced TCSExam, a 100 Lean-checked theoretical CS research tasks…
This is a dev post classified by AGK Intelligence as AI dev tools (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
@Kimi_Moonshot open-sourced TCSExam, a 100 Lean-checked theoretical CS research tasks covering theorem proving, solver engineering, constructions and open conjectures. The rank on the Full exam goes like this: ・GPT-6 Astra: 71.9 ・Kimi K3.1 Pro: 57.4 ・Kimi K3: 46.8 ・DeepSeek V4.1 Flash 1017: 46.0 ・GLM-5.3: 45.5 ・Qwen3.8 Max 0902: 44.8 ・Grok 4.6: 40.5 Idk why Claude is not on that list though, though it leads on the Lite exam with 72.3, followed by GPT-6 Astra with 67.0. You don't need GPUs in this at all. It's an agent-harness eval for Kimi Code, Claude Code, Codex, DeepSeek Harness etc. Ch
Posted by Javier Bits • priv/acc (5k followers) 1 h ago · 0 likes · 162 views · view the original post on X. Kept by the Dev Radar as AI dev tools.
More dev work like this
- ChatAndBuild is launching Living Brain. — @wallstengine
- I asked @bot to go through my original post’s replies and quotes to see the savings:… — @shuding
- 🫢牛逼！你的AI代理还在“瞎猜列名”？NVIDIA开源神器，直接把AI训练成懂业务的“数据打工人”！并且你能一眼看出AI代理是否说谎！ — @NFT_Chen
- Build videos in TypeScript — without Chrome in your render pipeline. — @DanKornas
- Drama 3 now cleans up after itself! 🔊 — @plotarmordev
- Made an automation so every morning GitHub Copilot prints this out for me. — @madebygps
- 💥码住！DeepSeek V4.1 Flash 1017 推理档位怎么用最省钱？！ — @NFT_Chen
- Claude、Codex 各开几个任务，窗口越开越多，刚才让谁查资料、谁还在改文件，切来切去很容易忘。 — @GitHub_Daily
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. 31.3k posts from 5k X accounts over the last 21 days, 9.3k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-04 14:12 UTC. Full method.