Carbon tops Abundant Labs agent benchmark with 14/20 vs Opus 5.5 and GPT-6
amankhan · x · 2026-11-11
Abundant Labs' agent coding benchmark (retweeted by amankhan) shows Carbon passing at least once on 14 of 20 tasks, ahead of GPT-6 Astra at 12 and Claude Opus 5.5 at 11.
- Carbon is the only one of the three to solve both the Stripe and Mastodon clone tasks
More from coding & agent
- No Claude account? This DSH plugin lets you try Claude-style Whiteboards anyway — dotey · 2026-11-11
- Running 6 concurrent ds41-flash agents: persistent enough to need pi-durable coordination — dbreunig · 2026-11-11
- OpenAI roundup: architecture details of four GPT-Live voice agent builds — pbbakkum · 2026-11-11
- Ex-Apple keyboard engineer Ken Kocienda open-sources Tug, a macOS AI coding app in beta — Scobleizer · 2026-11-11
- VS Code Copilot falls back from Computer Use and Python to PowerShell + COM to build an Excel workbook — dfinke · 2026-11-11
- LangChain's proactive agent engineering: agents will assign tasks to you — LangChain · 2026-11-11