Humans& multi-agent Ampersand matches frontier coding models at 70% lower cost
gharik · x · 2026-11-06
Humans& (@humansand) announced the multi-agent "Co-Coding" mode for Ampersand: trained to collaborate with people rather than given extra coding training, the multi-agent setup matches frontier coding models while being faster and cheaper.
- SWE-bench Pro v2 HARD-51: 92.2%, tying Fable 5.1 (70% cheaper) and Gemini 4 Argon, outperforming Astra, Muse Wonder, and Kimi K3.
- DeepSWE v1.1: 77.9%, on par with Gemini 4 Argon and ahead of Astra, Grok-4.7, Kimi K3, and Deepseek-v4-pro.
Available exclusively via their Agent API, with a $250 API credit offered for the next week. Commenter @jhong argued the AI that understands its user best will best deliver what the user wants from other agents and people — which is why Humans& matters.
More from coding & agent
- Apify RUN panel "Agents as first class citizens" lands in SF on Nov 10 — kleffew94 · 2026-11-06
- Executor v2 launches: Zapier/Retool-like automation fully drivable by code and AI agents — threepointone · 2026-11-06
- Y Combinator-backed Reflex raises $14M Series A, its Python framework hits 29k GitHub stars — ycombinator · 2026-11-06
- One diagram maps all the agent protocols: MCP, A2A, UCP, AP2, A2UI, AG-UI — rseroter · 2026-11-06
- Sutra: open-source terminal coding agent, lowest cost per solved task — cneuralnetwork · 2026-11-06
- From Greasemonkey to now: AI lets you mod any app just by describing the change — msfeldstein · 2026-11-06