Factory has released Droid 1.0, an updated model-independent coding agent harness that defaults to programmatic tool calling. This new feature allows the model to write JavaScript programs that execute tools within a sandboxed environment, enabling hundreds of tool calls per model request and significantly reducing token usage and cost. Factory reports that Droid 1.0 achieves a 65.2% pass rate on the Terminal-Bench 4 benchmark using Claude Opus 5.5, outperforming other leading coding agents in both performance and cost-efficiency. AI
IMPACT Enhances efficiency and reduces costs for AI-driven coding tasks by enabling more complex tool interactions.
RANK_REASON This is a new version of an existing software tool, not a frontier model release.
Read on Mastodon — mastodon.social →
- Claude Opus 5.5
- CodeAct
- Codex
- Cursor+
- Devin
- Droid 1.0
- Factory
- Factory Droid
- GPT-6.1 Sol
- Kimi k3
- macOS
- Microsoft Windows
- Node SDK
- Terminal-Bench 4
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →