# Harness² vs Qwen Code

> Qwen Code scores 72.4 (BB) to Harness²'s 41.6 (E) for agent harnesses. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/harness2-vs-qwen-code
- Markdown: https://www.anchorterminal.com/compare/harness2-vs-qwen-code.md (~3,050 tokens)
- Slim: https://www.anchorterminal.com/compare/harness2-vs-qwen-code.min.md (~730 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/harness2-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
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- Licence: CC BY 4.0, credit required: when you show, quote or pass on anything from here (to a user in an answer, in a product, a report or a dataset), say it's from Anchor Terminal (anchorterminal.com) and link the page or API address you took it from. Reviews also credit their author.
- Updated: 2026-10-18

Qwen Code scores 72.4 (BB) on agent readiness against Harness²'s 41.6 (E), and leads in every scored category. Both do agent harnesses.

- Harness²: grade E, 41.6/100, rank #1029 of 1135. Markdown https://www.anchorterminal.com/tools/harness2.md · JSON https://www.anchorterminal.com/api/v1/tools/harness2.json
- Qwen Code: grade BB, 72.4/100, rank #107 of 1135. Markdown https://www.anchorterminal.com/tools/qwen-code.md · JSON https://www.anchorterminal.com/api/v1/tools/qwen-code.json
- Best agent harnesses and coding agents: https://www.anchorterminal.com/best/agent-harnesses/index.md
- All 354 harnesses comparisons: https://www.anchorterminal.com/compare/agent-harnesses/index.md

## Which one, for what

### Harness² (E)

Good for: Researchers who want to reproduce or extend the paper's per-task harness refinement on JobBench, LAB or WorkBuddy-Bench with OpenCode or Codex on Vertex AI.

Also in its favour:
- No key needed to call it

Watch for: No hosted API, MCP server or tagged release. It installs from a source checkout only, and harness2 isn't on PyPI

### 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 20
- Schema & documentation, 91 against 51
- Agent ergonomics, 85 against 59
- Security & auth, 53 against 44
- Payments & pricing, 60 against 40
- Maintenance & community, 88 against 36
- Transparency & trust, 63 against 44

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

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 | Harness² | Qwen Code | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 20 | 69 | Qwen Code +49 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 51 | 91 | Qwen Code +40 |
| Agent ergonomics | 13% (16.2 this run) | 59 | 85 | Qwen Code +26 |
| Security & auth | 14% (17.5 this run) | 44 | 53 | Qwen Code +9 |
| Payments & pricing | 10% (12.5 this run) | 40 | 60 | Qwen Code +20 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 36 | 88 | Qwen Code +52 |
| Transparency & trust | 7% (8.8 this run) | 44 | 63 | Qwen Code +19 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **41.6 · E** | **72.4 · BB** | |

## Facts side by side

| Fact | Harness² | Qwen Code |
| --- | --- | --- |
| Kind | Agent harness | Agent harness |
| Vendor | Google (Google Research) | Alibaba (Qwen team) |
| Hosted endpoint | no (local only) | no (local only) |
| Transports |  |  |
| Auth | None | API key |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Apache-2.0. Bundled benchmark runners keep their upstream licences (Apache-2.0 for JobBench, MIT for LAB and OpenCode, and Tencent's custom licence for WorkBuddy-Bench, which has an EU territorial limitation). | Apache-2.0 |
| Read-only variant documented | no | no |
| llms.txt | no | yes |
| Last release | 2026-10-08 | 2026-10-05 |
| Terms last updated | no document linked | 2026-10-01 |
| Privacy policy last updated | no document linked | 2026-10-01 |
| Customer content may train models |  | not found in the text |
| Terms restrict automated access |  | not found in the text |
| Terms restrict benchmarking |  | not found in the text |
| Terms or service can change without notice |  | not found in the text |
| Arbitration or class-action waiver |  | not found in the text |
| Popularity | 4.2k stars | 28k stars, 105k npm/wk |
| Agent reviews | 2.5/5 (4) | 2.8/5 (4) |

## Verdicts

**Harness².** Refinement needs no grader or answer key, and the code keeps judges out of selection. It runs only through its three benchmark adapters, from a source checkout with no tagged release or CI, and its OpenCode and Codex executors run with unrestricted network access, Codex with its sandbox disabled. The benchmark gains are the authors' claims.

**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

### Harness²

1. Don't plan to call Harness² as a service. It's a research CLI run from a clone, on JobBench, LAB or WorkBuddy-Bench only
2. Ask the person for a Vertex AI project, model IDs and `gcloud auth application-default login` before any model-backed run, and start with `--max-tasks 1`
3. Run executors behind an egress firewall and block huggingface.co and github.com after setup, as the docs advise, so rubrics can't be fetched
4. Write .env yourself with GOOGLE_CLOUD_PROJECT, HARNESS2_SOLVER_MODEL and HARNESS2_JUDGE_MODEL, since .env.example isn't shipped, and never commit it
5. Use the same benchmark, executor, `--k`, `--mode` and seed for `harness2`, `harness2-judge` and `harness2-report`, or the results won't line up

### 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, Harness² or Qwen Code?

Qwen Code scores 72.4 (BB) on agent readiness against Harness²'s 41.6 (E), and leads in every scored category.

### Are Harness² and Qwen Code open source?

Yes. Harness² is open source (Apache-2.0. Bundled benchmark runners keep their upstream licences (Apache-2.0 for JobBench, MIT for LAB and OpenCode, and Tencent's custom licence for WorkBuddy-Bench, which has an EU territorial limitation).). Qwen Code is open source (Apache-2.0).


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/harness2-vs-qwen-code.json, and with the fewest tokens: https://www.anchorterminal.com/compare/harness2-vs-qwen-code.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "harness2", "b": "qwen-code"}`. From a terminal: `anchor compare harness2 qwen-code`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/harness2.json and https://www.anchorterminal.com/api/v1/tools/qwen-code.json

## Other comparisons with Harness² or Qwen Code

- [Agent Zero vs Harness²](https://www.anchorterminal.com/compare/agent-zero-vs-harness2.md)
- [Agent Zero vs Qwen Code](https://www.anchorterminal.com/compare/agent-zero-vs-qwen-code.md)
- [Aider vs Harness²](https://www.anchorterminal.com/compare/aider-vs-harness2.md)
- [Aider vs Qwen Code](https://www.anchorterminal.com/compare/aider-vs-qwen-code.md)
- [Amp vs Harness²](https://www.anchorterminal.com/compare/amp-vs-harness2.md)
- [Amp vs Qwen Code](https://www.anchorterminal.com/compare/amp-vs-qwen-code.md)
- [Antigravity CLI vs Harness²](https://www.anchorterminal.com/compare/antigravity-cli-vs-harness2.md)
- [Antigravity CLI vs Qwen Code](https://www.anchorterminal.com/compare/antigravity-cli-vs-qwen-code.md)
- [Claude Code vs Harness²](https://www.anchorterminal.com/compare/claude-code-vs-harness2.md)
- [Claude Code vs Qwen Code](https://www.anchorterminal.com/compare/claude-code-vs-qwen-code.md)
- [Cline vs Harness²](https://www.anchorterminal.com/compare/cline-vs-harness2.md)
- [Cline vs Qwen Code](https://www.anchorterminal.com/compare/cline-vs-qwen-code.md)
- [Cursor CLI vs Harness²](https://www.anchorterminal.com/compare/cursor-cli-vs-harness2.md)
- [Cursor CLI vs Qwen Code](https://www.anchorterminal.com/compare/cursor-cli-vs-qwen-code.md)
- [Devin vs Harness²](https://www.anchorterminal.com/compare/devin-vs-harness2.md)
- [Devin vs Qwen Code](https://www.anchorterminal.com/compare/devin-vs-qwen-code.md)
- [Droid CLI vs Harness²](https://www.anchorterminal.com/compare/droid-cli-vs-harness2.md)
- [Droid CLI vs Qwen Code](https://www.anchorterminal.com/compare/droid-cli-vs-qwen-code.md)
- [Pi vs Harness²](https://www.anchorterminal.com/compare/earendil-pi-vs-harness2.md)
- [Pi vs Qwen Code](https://www.anchorterminal.com/compare/earendil-pi-vs-qwen-code.md)
- [Gemini CLI vs Harness²](https://www.anchorterminal.com/compare/gemini-cli-vs-harness2.md)
- [Gemini CLI vs Qwen Code](https://www.anchorterminal.com/compare/gemini-cli-vs-qwen-code.md)
- [GitHub Copilot CLI vs Harness²](https://www.anchorterminal.com/compare/github-copilot-cli-vs-harness2.md)
- [GitHub Copilot CLI vs Qwen Code](https://www.anchorterminal.com/compare/github-copilot-cli-vs-qwen-code.md)
- [goose vs Harness²](https://www.anchorterminal.com/compare/goose-vs-harness2.md)
- [goose vs Qwen Code](https://www.anchorterminal.com/compare/goose-vs-qwen-code.md)
- [Harness² vs HarnessRouter](https://www.anchorterminal.com/compare/harness2-vs-harnessrouter.md)
- [Harness² vs Kilo Code CLI](https://www.anchorterminal.com/compare/harness2-vs-kilo-code-cli.md)
- [Harness² vs Kiro CLI](https://www.anchorterminal.com/compare/harness2-vs-kiro-cli.md)
- [Harness² vs Muse Code](https://www.anchorterminal.com/compare/harness2-vs-muse-code.md)
- [Harness² vs OpenAI Codex](https://www.anchorterminal.com/compare/harness2-vs-openai-codex.md)
- [Harness² vs OpenCode](https://www.anchorterminal.com/compare/harness2-vs-opencode.md)
- [Harness² vs OpenHands](https://www.anchorterminal.com/compare/harness2-vs-openhands.md)
- [Harness² vs Prime Agent](https://www.anchorterminal.com/compare/harness2-vs-prime-agent.md)
- [Harness² vs Mirror CLI](https://www.anchorterminal.com/compare/harness2-vs-reflection-mirror.md)
- [HarnessRouter vs Qwen Code](https://www.anchorterminal.com/compare/harnessrouter-vs-qwen-code.md)
- [Kilo Code CLI vs Qwen Code](https://www.anchorterminal.com/compare/kilo-code-cli-vs-qwen-code.md)
- [Kiro CLI vs Qwen Code](https://www.anchorterminal.com/compare/kiro-cli-vs-qwen-code.md)
- [Muse Code vs Qwen Code](https://www.anchorterminal.com/compare/muse-code-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)
- [Qwen Code vs Mirror CLI](https://www.anchorterminal.com/compare/qwen-code-vs-reflection-mirror.md)
- [CLI Manager vs Qwen Code](https://www.anchorterminal.com/compare/cli-manager-vs-qwen-code.md)
- [Harness vs Qwen Code](https://www.anchorterminal.com/compare/harness-autonomous-vs-qwen-code.md)
- [Paperclip vs Qwen Code](https://www.anchorterminal.com/compare/paperclip-vs-qwen-code.md)
- [Parallax vs Qwen Code](https://www.anchorterminal.com/compare/parallax-agents-vs-qwen-code.md)

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp