Ampersand hits 92.2% on SWE-bench Pro HARD-51 with collaborative co-coding
gharik · x · 2026-11-06
gharik boosts vpj's take on humansand's Ampersand: "making it better at collaborating with humans makes it better at collaborating with AIs." Key facts:
- Trained for human-AI collaborative coding rather than pure solo benchmarks
- Multi-agent mode scores 92.2% on SWE-bench Pro v2 HARD-51, matching Fable 5.1 at 70% lower cost and beating Astra, Muse Wonder, Kimi K3
- 77.9% on DeepSWE v1.1, on par with Gemini 4 Argon
- Available via its Agent API, with a $250 API credit for a week
More from coding & agent
- FastAPI creator tiangolo says he now uses voice-driven Codex way more after jxnlco's talk — jxnlco · 2026-11-06
- AWS WAF + Stripe lets sites charge AI agents via HTTP 402, with fiat payouts — jeff_weinstein · 2026-11-06
- The computable enterprise: capturing business logic that lives in employees' heads — vishalmisra · 2026-11-06
- Claude skills are useless — until you hook them to your actual business — aryanXmahajan · 2026-11-06
- Do you use MCP firewalls with Claude, Codex or Cursor in production? — vdobroskok · 2026-11-06
- Firecrawl launches Alexandria agent data layer with Benzinga, announces $75M Series B — devdigest · 2026-11-06