GPT-6 Astra leads BrowseComp for agentic web research at 91.5%.
This is a AI post classified by Jev as AI agents (a model release), kept by the AI Radar because it carries real work, not commentary.
GPT-6 Astra leads BrowseComp for agentic web research at 91.5%. Kimi K3 trails by just 0.3 points at 91.2%, but costs $14.25/M output versus Astra's $50/M. Claude Opus 5 is close behind at 90.8% for $25/M. With Merge Gateway, route research tasks based on performance and cost.
Posted by Merge (5.4k followers) 1 h ago · 25 likes · 126 views · view the original post on X. Kept by the AI Radar as AI agents.
More AI work like this
- Browserbase (@browserbase) is now available in Merge Agent Handler. — @merge_api
- Xiaomi has officially open-sourced the new MiMo-V2.6 family, featuring two native… — @itsvishaltwt
- NVIDIA Isaac ROS 5.0 brings AI agents to robotics development. 🤖 — @NVIDIARobotics
- How RL training can generalize to any harness and any task? — @bookwormengr
- META 🔥: Muse agent is being prepared to get integrations with Telegram, Messenger, and… — @testingcatalog
- 零人工答题！Claude 官方结业徽章正式到手🫡 全程 100% 靠 JEV + 小模型自主完成 — @SUOHA_AI
- Flyctor is one of the few AI projects where the product is already physical — @kiruwaaaaaa
- Encore for Rust is now rolling out to a small group of teams. — @encoredotdev
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. 41.6k posts from 5k X accounts over the last 14 days, 1.7k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-22 14:03 UTC. Full method.