Cognition's launch tweet left out the fact that open models beat SWE-2 Flash
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.
Cognition's launch tweet left out the fact that open models beat SWE-2 Flash The blog post has the full table, but the numbers they show don't match AA's runs on some of the benchmarks
Posted by Adam Holter (23.7k followers) 20 h ago · 24 likes · 2.4k views · view the original post on X. Kept by the AI Radar as AI coding agents.
More AI work like this
- Here are 10 new AI agent skills for Claude Code, Codex and more — @shushant_l
- The best tool for an AI agent is a markdown previewer. — @mfranz_on
- 🚀 Work across multiple agents, keep your favorite canvases close, and customize how you… — @code
- Bring your existing coding agent configuration to Command Code. — @CommandCodeAI
- I, or rather, Grok Bot made a Crash Bandicoot inspired runner game. — @chongdashu
- You have to send this to Claude Code or Codex 𝗯𝗲𝗳𝗼𝗿𝗲 𝗯𝗲𝗱! You'll wake up to a… — @Voxyz_ai
- Crazy. Full Terminal Bench 2.1, 89 tasks, 3 runs. My Mini Harness (~1,400 lines of… — @PawelHuryn
- THIS IS A F*CKING CHEAT CODE — @kyzoroX
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 15:10 UTC. Full method.