# Devin vs Qwen Code

> Qwen Code scores 72.4 (BB) on agent readiness against Devin's 55.7 (C), and leads in 5 of 7 scored categories. Devin leads on security & auth and transparency & trust. Both do agent harness. Category scores, facts, verdicts and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/devin-vs-qwen-code
- Markdown: https://www.anchorterminal.com/compare/devin-vs-qwen-code.md (~2,450 tokens)
- Slim: https://www.anchorterminal.com/compare/devin-vs-qwen-code.min.md (~680 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/devin-vs-qwen-code.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-08

Qwen Code scores 72.4 (BB) on agent readiness against Devin's 55.7 (C), and leads in 5 of 7 scored categories. Devin leads on security & auth and transparency & trust. Both do agent harness.

- Devin: grade C, 55.7/100, rank #505 of 722. Markdown https://www.anchorterminal.com/tools/devin.md · JSON https://www.anchorterminal.com/api/v1/tools/devin.json
- Qwen Code: grade BB, 72.4/100, rank #93 of 722. Markdown https://www.anchorterminal.com/tools/qwen-code.md · JSON https://www.anchorterminal.com/api/v1/tools/qwen-code.json

## Which one, for what

### Devin (C)

Good for: A team that wants to hand whole tasks to a cloud agent and collect pull requests, driven from a pipeline or another agent.

Ahead on:
- Security & auth, 72 against 53
- Transparency & trust, 69 against 63

Also in its favour:
- A hosted endpoint, with nothing to install

Watch for: www.devinstatus.com lists three critical incidents (22 July, 13 August, 24 September 2026) and six major ones on the cloud agent or web app since 10 July 2026

### Qwen Code (BB)

Good for: Developers and CI jobs that want an open-source harness tied to no single model vendor, with run budgets and SDKs.

Ahead on:
- Reliability, 69 against 30
- Schema & documentation, 91 against 80
- Agent ergonomics, 85 against 62
- Payments & pricing, 60 against 20
- Maintenance & community, 88 against 63

Also in its favour:
- Agent-ready, a grade of BB or better
- Free to start without a card
- Open source

Watch for: The default approval mode is Auto, where an LLM classifier approves tool calls, and sandboxing and folder trust are both off by default


## Score by category

| Category | Weight | Devin | Qwen Code | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 30 | 69 | Qwen Code +39 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 80 | 91 | Qwen Code +11 |
| Agent ergonomics | 13% (16.2 this run) | 62 | 85 | Qwen Code +23 |
| Security & auth | 14% (17.5 this run) | 72 | 53 | Devin +19 |
| Payments & pricing | 10% (12.5 this run) | 20 | 60 | Qwen Code +40 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 63 | 88 | Qwen Code +25 |
| Transparency & trust | 7% (8.8 this run) | 69 | 63 | Devin +6 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **55.7 · C** | **72.4 · BB** | |

## Facts side by side

| Fact | Devin | Qwen Code |
| --- | --- | --- |
| Kind | Agent harness | Agent harness |
| Vendor | Cognition AI, Inc. | Alibaba (Qwen team) |
| Hosted endpoint | `https://mcp.devin.ai/mcp` | no (local only) |
| Transports | HTTP |  |
| Auth | API key | API key |
| Pricing | Freemium | Free |
| x402 | no | no |
| Licence | Proprietary service under Cognition's Platform Terms of Service | Apache-2.0 |
| Tools exposed | 13 | none |
| Read-only variant documented | yes | no |
| llms.txt | yes | yes |
| Last release | 2026-10-07 | 2026-10-05 |
| Terms last updated | 2026-06-30 | 2026-10-01 |
| Privacy policy last updated | 2026-03-09 | 2026-10-01 |
| Customer content may train models | yes, with an opt-out | not found in the text |
| Terms restrict automated access | not found in the text | not found in the text |
| Terms restrict benchmarking | yes | not found in the text |
| Terms or service can change without notice | not found in the text | not found in the text |
| Arbitration or class-action waiver | yes | not found in the text |
| Popularity | none | 28k stars, 105k npm/wk |

## Verdicts

**Devin.** The v3 API is well specified, with a public OpenAPI 3.1 file covering 239 operations, problem+json errors, cursor pagination and service-user keys tied to roles. The status page records three critical and several major incidents on the cloud agent between 22 July and 24 September 2026, and no rate limit figures or retry guidance were found in the reviewed documentation.

**Qwen Code.** Apache-2.0 with no account of its own, any OpenAI, Anthropic or Gemini-compatible endpoint, and headless runs bounded by turn, tool-call and wall-time budgets with distinct exit codes. Out of the box, Auto mode lets an LLM classifier approve tool calls, with the sandbox and folder trust both off. Usage statistics are on by default.

## Before you call either

### Devin

1. Use a `cog_` service-user key with the Member role. Legacy `apk_` keys fail against v3 and the MCP server with 401 or 403
2. Set `max_acu_limit` on every session you create. Usage is metered by the work done and has no published unit rate
3. Session creation is not idempotent in v3. After a timeout, list sessions by tag before creating again
4. Enterprise keys and personal access tokens must send `X-Org-Id` to the MCP server. Organisation-scoped keys resolve it automatically
5. Create scheduled work as an automation. POST to the schedules endpoint returns 403 for migrated organisations since 24 September 2026

### Qwen Code

1. Pass `--approval-mode` on every run. The settings default is `auto`, and one docs page says headless runs default to asking, so don't rely on either
2. Add `--max-session-turns`, `--max-wall-time` and `--max-tool-calls`. All three are unlimited by default. Exit 53 is the turn limit and 55 a budget
3. `--yolo` doesn't turn on a sandbox. Add `--sandbox`, or on Linux set `tools.executionSandbox` with `network` set to `closed`
4. Set `QWEN_USAGE_STATISTICS_ENABLED=false` to stop usage statistics
5. Authenticate with `OPENAI_API_KEY`, `OPENAI_BASE_URL` and `OPENAI_MODEL` in CI. The browser sign-in is discontinued

## Questions

### Which is better for AI agents, Devin or Qwen Code?

Qwen Code scores 72.4 (BB) on agent readiness against Devin's 55.7 (C), and leads in 5 of 7 scored categories. Devin leads on security & auth and transparency & trust.

### Are Devin and Qwen Code open source?

No open-source release is listed for Devin. Qwen Code is open source (Apache-2.0).


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/devin-vs-qwen-code.json, and with the fewest tokens: https://www.anchorterminal.com/compare/devin-vs-qwen-code.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "devin", "b": "qwen-code"}`. From a terminal: `anchor compare devin qwen-code`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/devin.json and https://www.anchorterminal.com/api/v1/tools/qwen-code.json

## Other comparisons with Devin or Qwen Code

- [Aider vs Devin](https://www.anchorterminal.com/compare/aider-vs-devin.md)
- [Aider vs Qwen Code](https://www.anchorterminal.com/compare/aider-vs-qwen-code.md)
- [Amp vs Devin](https://www.anchorterminal.com/compare/amp-vs-devin.md)
- [Amp vs Qwen Code](https://www.anchorterminal.com/compare/amp-vs-qwen-code.md)
- [Claude Code vs Devin](https://www.anchorterminal.com/compare/claude-code-vs-devin.md)
- [Claude Code vs Qwen Code](https://www.anchorterminal.com/compare/claude-code-vs-qwen-code.md)
- [Cline vs Devin](https://www.anchorterminal.com/compare/cline-vs-devin.md)
- [Cline vs Qwen Code](https://www.anchorterminal.com/compare/cline-vs-qwen-code.md)
- [Cursor CLI vs Devin](https://www.anchorterminal.com/compare/cursor-cli-vs-devin.md)
- [Cursor CLI vs Qwen Code](https://www.anchorterminal.com/compare/cursor-cli-vs-qwen-code.md)
- [Devin vs Pi](https://www.anchorterminal.com/compare/devin-vs-earendil-pi.md)
- [Devin vs Gemini CLI](https://www.anchorterminal.com/compare/devin-vs-gemini-cli.md)
- [Devin vs GitHub Copilot CLI](https://www.anchorterminal.com/compare/devin-vs-github-copilot-cli.md)
- [Devin vs goose](https://www.anchorterminal.com/compare/devin-vs-goose.md)
- [Devin vs Kiro CLI](https://www.anchorterminal.com/compare/devin-vs-kiro-cli.md)
- [Devin vs OpenAI Codex](https://www.anchorterminal.com/compare/devin-vs-openai-codex.md)
- [Devin vs OpenCode](https://www.anchorterminal.com/compare/devin-vs-opencode.md)
- [Devin vs OpenHands](https://www.anchorterminal.com/compare/devin-vs-openhands.md)
- [Devin vs Prime Agent](https://www.anchorterminal.com/compare/devin-vs-prime-agent.md)
- [Pi vs Qwen Code](https://www.anchorterminal.com/compare/earendil-pi-vs-qwen-code.md)
- [Gemini CLI vs Qwen Code](https://www.anchorterminal.com/compare/gemini-cli-vs-qwen-code.md)
- [GitHub Copilot CLI vs Qwen Code](https://www.anchorterminal.com/compare/github-copilot-cli-vs-qwen-code.md)
- [goose vs Qwen Code](https://www.anchorterminal.com/compare/goose-vs-qwen-code.md)
- [Kiro CLI vs Qwen Code](https://www.anchorterminal.com/compare/kiro-cli-vs-qwen-code.md)
- [OpenAI Codex vs Qwen Code](https://www.anchorterminal.com/compare/openai-codex-vs-qwen-code.md)
- [OpenCode vs Qwen Code](https://www.anchorterminal.com/compare/opencode-vs-qwen-code.md)
- [OpenHands vs Qwen Code](https://www.anchorterminal.com/compare/openhands-vs-qwen-code.md)
- [Prime Agent vs Qwen Code](https://www.anchorterminal.com/compare/prime-agent-vs-qwen-code.md)
- [Devin vs Paperclip](https://www.anchorterminal.com/compare/devin-vs-paperclip.md)
- [Paperclip vs Qwen Code](https://www.anchorterminal.com/compare/paperclip-vs-qwen-code.md)