# Factory releases Droid 1.0, an agent harness that runs hundreds of tool calls per model request

Canonical: https://theagenticweekly.com/news/factory-droid-1-0 · Evidence: Reported · First seen: 2026-10-31 12:44 UTC · Source published: not stated by the source · Brief published: 2026-11-01 00:03 UTC · Updated: 2026-11-01 00:03 UTC · Author: Agentic Weekly

> Factory says Droid 1.0, released October 29, 2026, is "more accurate, efficient, and faster than ever before". In Factory's own Terminal-Bench 4 runs with GPT-6.1 Sol, Droid passed 57.6% of tasks at $0.79 per passed task, against 54.0% for Codex.

Models in this brief: [GPT-6.1 Terra](https://theagenticweekly.com/models/gpt-6-1-terra), [GPT-6.1 Sol](https://theagenticweekly.com/models/gpt-6-1-sol), [Claude Opus 5.5](https://theagenticweekly.com/models/claude-opus-5-5), [Claude Fable 5.1](https://theagenticweekly.com/models/claude-fable-5-1), [GPT-6 Astra](https://theagenticweekly.com/models/gpt-6-astra), [Kimi K3](https://theagenticweekly.com/models/kimi-k3)

## What changed

- Droid 1.0 adds Script mode: the model writes JavaScript that runs in a sandbox and can make hundreds of tool calls in one model request, instead of one model call per tool call.
- Factory says Script mode is on by default for GPT-6.1 Sol, GPT-6.1 Terra, GPT-6 Astra, Claude Fable 5.1, Claude Opus 5.5, Kimi K3 and several older models.
- Factory's own Terminal-Bench 4 numbers: with Claude Opus 5.5, Droid passed 65.2% at $4.73 per passed task versus 57.6% for Claude Code; with GPT-6.1 Sol, 57.6% versus 54.0% for Codex.
- Factory says the app opens faster (first paint 1,839 to 488 ms) and quits faster (median 648 to 30 ms).
- Droid 1.0 ships as a desktop app for macOS and Windows and a terminal UI, plus the Droid SDK (@factory/droid-sdk), which runs the same Droid as the CLI from Node.
- Factory's changelog lists CLI v1.0.0 and Desktop v1.0.0 on October 29, 2026, followed by v1.1.0 on October 30.

## In the source's words

> "Droid is our agent harness."
> (Factory: Droid 1.0 announcement, https://factory.com/news/frontier-harness)

> "A Script can make hundreds of tool calls in one model request"
> (Factory: Droid 1.0 announcement, https://factory.com/news/frontier-harness)

## Early verdict

Worth a look if you run long agent sessions and want one harness across Claude and GPT models, but treat the head-to-head numbers as vendor claims until independent runs appear. (Basis: Based only on Factory's announcement and changelog; we have not run Droid 1.0.)

## What we have not verified

- All benchmark, cost and speed figures are Factory's own; we did not run Terminal-Bench 4 or compare harnesses ourselves.
- Factory reran some Claude Opus 5.5 trials on Claude Opus 5 after content-moderation stops, per its methodology; we did not check how that affects the comparison.
- We did not install Droid 1.0 or the Droid SDK.

## Timeline

- Source published: not stated by the source
- First seen by our watcher: 2026-10-31 12:44 UTC (via MarkTechPost (press signal))
- Brief published: 2026-11-01 00:03 UTC

## Sources

- [Factory: Droid 1.0, building a frontier harness](https://factory.com/news/frontier-harness) (primary source) (fetched 2026-10-31)
- [Factory changelog](https://docs.factory.com/changelog/release-notes) (primary source) (fetched 2026-10-31)

## Related

- [GPT-6.1 Terra: specs, price and alternatives](https://theagenticweekly.com/models/gpt-6-1-terra)
- [GPT-6.1 Sol: specs, price and alternatives](https://theagenticweekly.com/models/gpt-6-1-sol)
- [Claude Opus 5.5: specs, price and alternatives](https://theagenticweekly.com/models/claude-opus-5-5)
- [Claude Fable 5.1: specs, price and alternatives](https://theagenticweekly.com/models/claude-fable-5-1)
- [GPT-6 Astra: specs, price and alternatives](https://theagenticweekly.com/models/gpt-6-astra)
- [Kimi K3: specs, price and alternatives](https://theagenticweekly.com/models/kimi-k3)
- [Claude Opus 5.5 vs GPT-6.1 Sol](https://theagenticweekly.com/compare/claude-opus-5-5-vs-gpt-6-1-sol)
- [Gemini 4 Argon vs GPT-6.1 Sol](https://theagenticweekly.com/compare/gemini-4-argon-vs-gpt-6-1-sol)
- [Claude Sonnet 5.5 vs GPT-6.1 Sol](https://theagenticweekly.com/compare/claude-sonnet-5-5-vs-gpt-6-1-sol)
- [Claude Code: verdict and setup guide](https://theagenticweekly.com/tools/claude-code)
- [Codex CLI: verdict and setup guide](https://theagenticweekly.com/tools/codex-cli)
- [opencode: verdict and setup guide](https://theagenticweekly.com/tools/opencode)
- [Cursor: verdict and setup guide](https://theagenticweekly.com/tools/cursor)
- [Devin: verdict and setup guide](https://theagenticweekly.com/tools/devin)
- [All news briefs](https://theagenticweekly.com/news)
- [This week's releases](https://theagenticweekly.com/this-week)
- [New AI models this week](https://theagenticweekly.com/models/this-week)

## How to cite

Agentic Weekly, "Factory releases Droid 1.0, an agent harness that runs hundreds of tool calls per model request", published 2026-11-01 00:03 UTC, https://theagenticweekly.com/news/factory-droid-1-0