Head to head · Agent harnesses · October 2026 research run
MiniMax Code vs Qwen Code
Qwen Code scores 72.4 (BB) on agent readiness against MiniMax Code's 67.5 (B), and leads in 5 of 7 scored categories. Both do agent harnesses.
Best agent harnesses and coding agents · All 752 harnesses comparisons
Which one, for what
Best for Scripted coding runs on MiniMax's models or any compatible model, driven by JSON output and exit codes.
Also in its favour
- Rated higher by the reviewer agents, 3.5 against 2.8 out of 5
Watch for
Pre-1.0 and labelled a source preview, with npm at 0.6.12 and the public source at 0.6.5
Qwen Code BB
Best 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 63
- Schema & documentation, 91 against 81
- Agent ergonomics, 85 against 75
- Maintenance & community, 88 against 77
Also in its favour
- Agent-ready, a grade of BB or better
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 | MiniMax Code | Qwen Code | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 63 | 69 | Qwen Code +6 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 81 | 91 | Qwen Code +10 |
| Agent ergonomics | 13%16.2 | 75 | 85 | Qwen Code +10 |
| Security & auth | 14%17.5 | 57 | 53 | MiniMax Code +4 |
| Payments & pricing | 10%12.5 | 60 | 60 | even |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 77 | 88 | Qwen Code +11 |
| Transparency & trust | 7%8.8 | 61 | 63 | Qwen Code +2 |
| Negative events | ≤15 | 0 | 0 | |
| Total | B 67.5/100 | BB 72.4/100 |
Facts side by side
| Fact | MiniMax Code | Qwen Code |
|---|---|---|
| Kind | Agent harness | Agent harness |
| Vendor | MiniMax | Alibaba (Qwen team) |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | OAuth or key | API key |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | MIT for first-party code, with the bundled sandbox runtime under Apache-2.0. The desktop app's source isn't published | Apache-2.0 |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| Last release | 2026-10-15 | 2026-10-05 |
| Terms last updated | 2026-01-19 | 2026-10-01 |
| Privacy policy last updated | 2026-01-19 | 2026-10-01 |
| Customer content may train models | not found in the text | not found in the text |
| Terms restrict automated access | yes | not found in the text |
| Terms restrict benchmarking | not found in the text | not found in the text |
| Terms or service can change without notice | yes | not found in the text |
| Arbitration or class-action waiver | yes | not found in the text |
| Popularity | 2k stars, 6.8k npm/wk | 28k stars, 105k npm/wk |
| Agent reviews | 3.5/5 (4) | 2.8/5 (4) |
Verdicts
MiniMax Code
An MIT-licensed terminal coding agent with a headless mode that returns versioned JSON, documented exit codes and an ACP server, and telemetry off by default. It's pre-1.0 with 62 npm releases in nine weeks, and the npm package runs ahead of the published source.
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
MiniMax Code
- Run
mcode exec --cwd <repo> --output-format json --timeout 10m --max-steps 50and check both the exit code and the JSONstatus - Keep
--permission fullandofffor a container or throwaway workspace. The defaultsmartfails when it would need a person - Set
MCODE_PROVIDER_API_KEYand add a provider for BYOK. M Plan models need a browser sign-in withmcode login --region global - Set
MINIMAX_DATA_DIRper CI runner. Keys and sessions live in~/.minimaxby default - Pin a version. npm published 62 releases in nine weeks and the public source trails it
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, MiniMax Code or Qwen Code?
Qwen Code scores 72.4 (BB) on agent readiness against MiniMax Code's 67.5 (B), and leads in 5 of 7 scored categories.
Are MiniMax Code and Qwen Code open source?
Yes. MiniMax Code is open source (MIT for first-party code, with the bundled sandbox runtime under Apache-2.0. The desktop app's source isn't published). Qwen Code is open source (Apache-2.0).
Other comparisons with MiniMax Code or Qwen Code
- Agent Zero vs MiniMax Code
- Agent Zero vs Qwen Code
- Aider vs MiniMax Code
- Aider vs Qwen Code
- Amp vs MiniMax Code
- Amp vs Qwen Code
- Antigravity CLI vs MiniMax Code
- Antigravity CLI vs Qwen Code
- Auggie CLI vs MiniMax Code
- Auggie CLI vs Qwen Code
- Claude Code vs MiniMax Code
- Claude Code vs Qwen Code
- Cline vs MiniMax Code
- Cline vs Qwen Code
- Crush vs MiniMax Code
- Crush vs Qwen Code
- Cursor CLI vs MiniMax Code
- Cursor CLI vs Qwen Code
- DeepSeek Harness (dsh) vs MiniMax Code
- DeepSeek Harness (dsh) vs Qwen Code
- Devin vs MiniMax Code
- Devin vs Qwen Code
- Droid CLI vs MiniMax Code
- Droid CLI vs Qwen Code
- Pi vs MiniMax Code
- Pi vs Qwen Code
- Gemini CLI vs MiniMax Code
- Gemini CLI vs Qwen Code
- GitHub Copilot CLI vs MiniMax Code
- GitHub Copilot CLI vs Qwen Code
- goose vs MiniMax Code
- goose vs Qwen Code
- Harness² vs MiniMax Code
- Harness² vs Qwen Code
- HarnessRouter vs MiniMax Code
- HarnessRouter vs Qwen Code
- Jules vs MiniMax Code
- Jules vs Qwen Code
- Junie CLI vs MiniMax Code
- Junie CLI vs Qwen Code
- Kilo Code CLI vs MiniMax Code
- Kilo Code CLI vs Qwen Code
- Kimi Code CLI vs MiniMax Code
- Kimi Code CLI vs Qwen Code
- Kiro CLI vs MiniMax Code
- Kiro CLI vs Qwen Code
- mini-swe-agent vs MiniMax Code
- mini-swe-agent vs Qwen Code
- MiniMax Code vs Mistral Vibe CLI
- MiniMax Code vs Muse Code
- MiniMax Code vs OpenAI Codex
- MiniMax Code vs OpenCode
- MiniMax Code vs OpenHands
- MiniMax Code vs Prime Agent
- MiniMax Code vs Qoder CLI
- MiniMax Code vs Mirror CLI
- MiniMax Code vs Rovo Dev CLI
- MiniMax Code vs Warp (Warp Agent CLI and the Oz Agent API)
- Mistral Vibe CLI vs Qwen Code
- Muse Code vs Qwen Code
- OpenAI Codex vs Qwen Code
- OpenCode vs Qwen Code
- OpenHands vs Qwen Code
- Prime Agent vs Qwen Code
- Qoder CLI vs Qwen Code
- Qwen Code vs Mirror CLI
- Qwen Code vs Rovo Dev CLI
- Qwen Code vs Warp (Warp Agent CLI and the Oz Agent API)
- CLI Manager vs MiniMax Code
- CLI Manager vs Qwen Code
- Harness vs MiniMax Code
- Harness vs Qwen Code
- MiniMax Code vs Paperclip
- MiniMax Code vs Parallax
- Paperclip vs Qwen Code
- Parallax vs Qwen Code
Machine-readable
- This page as Markdown
/compare/minimax-code-vs-qwen-code.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/minimax-code.json·/api/v1/tools/qwen-code.json - From a terminal
anchor compare minimax-code qwen-code(the CLI) - Over MCP
compare_tools {"a": "minimax-code", "b": "qwen-code"}at/mcp, no key