tested both models with same prompt at highest reasoning available and results came out…
This is a AI post classified by AGK Intelligence as AI coding agents (a model release), kept by the AI Radar because it carries real work, not commentary.
haiku 5.5 vs swe 2 flash tested both models with same prompt at highest reasoning available and results came out almost same > haiku took 70 mins to make this and cost $0.2 > swe 2 flash took 15 mins to take and cost $0.0 both models made almost same game but swe was super fast and free right now in devin so you can give it for free which model did better here?
Posted by J A Z I I (12.8k followers) 1 days ago · 9 likes · 308 views · view the original post on X. Kept by the AI Radar as AI coding agents.
More AI work like this
- BREAKING: same open model, same provider, same reasoning budget. Swap only the coding… — @guilleflorvs
- Cursor was about to raise a few billion dollars. Then it sold to SpaceX for $60B. — @guilleflorvs
- The tricky part of sandboxing is often what happens at the boundary with the host. — @AgenticAIFdn
- does paying more for AI get you better 3D? — @DataChaz
- The Daytona Playbook: From $1M to $100M in a Year — @guilleflorvs
- Claude Code 2.1.318 对用 claude -p 挂定时任务的人很实用： — @wei_wang
- Just one short prompt can improve whatever Claude Code just made. — @undefinedKi
- Here are 10 new AI agent skills for Claude Code, Codex and more — @shushant_l
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. 65.5k 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 16:50 UTC. Full method.