Dev benchmarks agent harnesses, says opencode beats PI, OpenClaw and Hermes by a huge margin
dh7net · x · 2026-09-29
Developer dh7net reports that after running real-workload agent benchmarks, opencode is the best coding agent out there — by a huge margin, while PI, OpenClaw and Hermes all perform noticeably worse, apologizing to the respective authors.
The claim is based on airbench.ai (detailed in the companion post), a benchmark designed to test your own agent setup on realistic tasks rather than rank frontier models, making this a notable practitioner-side comparison of agent harnesses.
More from coding & agent
- Steal this prompt: Opus 5.5 plus Runway MCP for polished motion design videos — notiansans · 2026-09-29
- Pluto launches in beta: a personal agent with inbox, memory and a computer — Rasmic · 2026-09-29
- Anthropic adds official eval-building and hillclimbing workflow to Claude Code skill — ClaudeDevs · 2026-09-29
- Anthropic engineer: don't run Sonnet at max effort — use Opus instead — edwinarbus · 2026-09-29
- Claude Sonnet 5.5 turns a 60×46 pixel emoji into a printable 3D model in hours — claudeai · 2026-09-29
- Hugging Face agent attack postmortem: allowlists gate where agents go, not what they do — kimmonismus · 2026-09-29