Kimi K3.1 - max reasoning - scored 89.4% on my terminal-bench 4 subset. Sol Max is @…
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 K3.1 - max reasoning - scored 89.4% on my terminal-bench 4 subset. Sol Max is @ 64.2 for similar cost. The traces look pretty clean, with less benchmark awareness than I expected. You can get them here: https://fast-agent.ai/benchmarks/run/?id=tb4-kimik31pro-max
Posted by Shaun Smith (1.3k followers) 1 h ago · 0 likes · 41 views · view the original post on X. Kept by the Dev Radar as AI dev tools. Tools mentioned: fast-agent.
More dev work like this
- 写项目文档要配一张架构图，光去各家官网找 Logo、对齐连线就得折腾一下午，画完箭头还压着字。 — @GitHub_Daily
- the next Polyphonic // Mnemos update is going to make you pee your pantaloons. Fable 5.5… — @RileyRalmuto
- launching today on locul ai (grokbot alternative) — @_junaidkhalid1
- 💥绝了！DeepSeek Harness + DeepSeek V4.1 Flash 1017 一键生成可交互雨夜日式便利店! 效果不输Opus 5.5！ — @NFT_Chen
- Catch gaps in your AI coding spec before they become code. — @DanKornas
- What can AI tooling abstract away when you build for multiple platforms? — @callstackio
- 太卷了吧！OpenDesign 这波是不是疯了？ — @NFT_Chen
- 🔥学生党狂喜！Mistral 学生计划太香了！$5.99/月（原价$14.99）直接拿价值约$165的用量！ — @NFT_Chen
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. 31.8k posts from 5k X accounts over the last 21 days, 9.5k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 13:13 UTC. Full method.