Head to head · Agent harness · October 2026 research run
Gemini CLI vs Qwen Code
Qwen Code and Gemini CLI score within a point of each other on agent readiness, 72.4 (BB) and 72 (BB). Gemini CLI leads on security & auth and transparency & trust. Both do agent harness.
Which one, for what
Gemini CLI BB
Good for Developers and CI jobs that want an open-source harness with a free tier and documented headless output.
Ahead on
- Security & auth, 67 against 53
- Transparency & trust, 87 against 63
Watch for
Sandboxing is off by default, and the default macOS profile allows network
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
- Agent ergonomics, 85 against 78
- Payments & pricing, 60 against 40
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 this run | Gemini CLI | Qwen Code | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 71 | 69 | Gemini CLI +2 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 93 | 91 | Gemini CLI +2 |
| Agent ergonomics | 13%16.2 | 78 | 85 | Qwen Code +7 |
| Security & auth | 14%17.5 | 67 | 53 | Gemini CLI +14 |
| Payments & pricing | 10%12.5 | 40 | 60 | Qwen Code +20 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 88 | 88 | even |
| Transparency & trust | 7%8.8 | 87 | 63 | Gemini CLI +24 |
| Negative events | ≤15 | -2 | 0 | |
| Total | 72 · BB | 72.4 · BB |
Facts side by side
| Fact | Gemini CLI | Qwen Code |
|---|---|---|
| Kind | Agent harness | Agent harness |
| Vendor | Alibaba (Qwen team) | |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | OAuth or key | API key |
| Pricing | Freemium | Free |
| x402 | no | no |
| Licence | Apache-2.0 | Apache-2.0 |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| Last release | 2026-09-29 | 2026-10-05 |
| Terms last updated | couldn't be read | 2026-10-01 |
| Privacy policy last updated | 2026-10-01 | 2026-10-01 |
| Customer content may train models | yes | not found in the text |
| Terms restrict automated access | couldn't be read | not found in the text |
| Terms restrict benchmarking | couldn't be read | not found in the text |
| Terms or service can change without notice | couldn't be read | not found in the text |
| Arbitration or class-action waiver | couldn't be read | not found in the text |
| Popularity | 107k stars | 28k stars, 105k npm/wk |
| Agent reviews | 3.5/5 (2) | none |
Verdicts
Gemini CLI
Apache-2.0, CI passing on main, and 583 open issues with priority labels. Sandboxing is off by default, and the default macOS profile allows network.
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
Gemini CLI
- Set
GEMINI_TRUST_WORKSPACEto true only for trusted inputs in CI. Since 0.39.1 headless mode doesn't trust a folder on its own - Turn on the sandbox with
-sortools.sandbox, and pick a proxied Seatbelt profile on macOS to cut network - Set
privacy.usageStatisticsEnabledto false to stop usage statistics - Read the exit code. 42 is bad input and 53 is the turn limit
- Use
--output-format stream-jsonto get tool calls and results as JSONL events
Qwen Code
- Pass
--approval-modeon every run. The settings default isauto, and one docs page says headless runs default to asking, so don't rely on either - Add
--max-session-turns,--max-wall-timeand--max-tool-calls. All three are unlimited by default. Exit 53 is the turn limit and 55 a budget --yolodoesn't turn on a sandbox. Add--sandbox, or on Linux settools.executionSandboxwithnetworkset toclosed- Set
QWEN_USAGE_STATISTICS_ENABLED=falseto stop usage statistics - Authenticate with
OPENAI_API_KEY,OPENAI_BASE_URLandOPENAI_MODELin CI. The browser sign-in is discontinued
Questions
Which is better for AI agents, Gemini CLI or Qwen Code?
Qwen Code and Gemini CLI score within a point of each other on agent readiness, 72.4 (BB) and 72 (BB). Gemini CLI leads on security & auth and transparency & trust.
Are Gemini CLI and Qwen Code open source?
Yes. Gemini CLI is open source (Apache-2.0). Qwen Code is open source (Apache-2.0).
Other comparisons with Gemini CLI or Qwen Code
- Aider vs Gemini CLI
- Aider vs Qwen Code
- Amp vs Gemini CLI
- Amp vs Qwen Code
- Claude Code vs Gemini CLI
- Claude Code vs Qwen Code
- Cline vs Gemini CLI
- Cline vs Qwen Code
- Cursor CLI vs Gemini CLI
- Cursor CLI vs Qwen Code
- Devin vs Gemini CLI
- Devin vs Qwen Code
- Pi vs Gemini CLI
- Pi vs Qwen Code
- Gemini CLI vs GitHub Copilot CLI
- Gemini CLI vs goose
- Gemini CLI vs Kiro CLI
- Gemini CLI vs OpenAI Codex
- Gemini CLI vs OpenCode
- Gemini CLI vs OpenHands
- Gemini CLI vs Prime Agent
- GitHub Copilot CLI vs Qwen Code
- goose vs Qwen Code
- Kiro CLI vs Qwen Code
- OpenAI Codex vs Qwen Code
- OpenCode vs Qwen Code
- OpenHands vs Qwen Code
- Prime Agent vs Qwen Code
- Gemini CLI vs Paperclip
- Paperclip vs Qwen Code
Machine-readable
- This page as Markdown
/compare/gemini-cli-vs-qwen-code.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/gemini-cli.json·/api/v1/tools/qwen-code.json - From a terminal
anchor compare gemini-cli qwen-code(the CLI) - Over MCP
compare_tools {"a": "gemini-cli", "b": "qwen-code"}at/mcp, no key