GPT-6 Luna is a step function improvement from it's predecessor scoring 11% higher in…
This is a dev post classified by Jev as AI dev tools (a launch), kept by the Dev Radar because it carries real work, not commentary.
GPT-6 Luna is a step function improvement from it's predecessor scoring 11% higher in accuracy on our browser agent tasks. GPT-6 Sol scores 2% better in accuracy, but costs 20x more per task than Luna.
Posted by Stagehand (5.5k followers) 2 h ago · 11 likes · 455 views · view the original post on X. Kept by the Dev Radar as AI dev tools.
More dev work like this
- useful tip for Opus 5.5: — @RLanceMartin
- Fable 5.1 vs GPT-6 Astra at computer-use. — @coastyai
- You can now run locally Qwen Image 2.1 on AMD, Intel, and Mac on 2GB VRAM. — @0x0SojalSec
- OpenAI推出GPT-6 Sol与Luna：继承Astra能力，API价格腰斩50% — @MetaEraCN
- this is how i orchestrate coding agents now — @jacsebl
- 双持省钱绝招！昨天半夜冲了 Claude Code Pro，20 美金，这次性价比直接拉满： — @LinearUncle
- this agent — @sydneyrunkle
- PCB automation gets risky when the agent can’t work with the real design. — @DanKornas
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 21.7k posts from 5k X accounts over the last 21 days, 2.5k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-23 02:31 UTC. Full method.