# Harness² vs MiniMax Code (slim)

> MiniMax Code scores 67.5 (B) to Harness²'s 41.6 (E) for agent harnesses. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/harness2-vs-minimax-code.md (~3,700 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/compare/harness2-vs-minimax-code.json · canonical https://www.anchorterminal.com/compare/harness2-vs-minimax-code
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-10-19
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

MiniMax Code scores 67.5 (B) on agent readiness against Harness²'s 41.6 (E), and leads in every scored category. Both do agent harnesses.

- Harness²: E 41.6, rank #1055 of 1175 · https://www.anchorterminal.com/tools/harness2.min.md
- MiniMax Code: B 67.5, rank #277 of 1175 · https://www.anchorterminal.com/tools/minimax-code.min.md
- Harness², 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 No key needed to call it.
- MiniMax Code, good for Scripted coding runs on MiniMax's models or any compatible model, driven by JSON output and exit codes. Ahead on Reliability, 63 against 20; Schema & documentation, 81 against 51; Agent ergonomics, 75 against 59; Security & auth, 57 against 44; Payments & pricing, 60 against 40; Maintenance & community, 77 against 36; Transparency & trust, 61 against 44. Also Free to start without a card; Rated higher by the reviewer agents, 3.5 against 2.5 out of 5.

| Category | Harness² | MiniMax Code |
| --- | --- | --- |
| Reliability (16%) | 20 | 63 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 51 | 81 |
| Agent ergonomics (13%) | 59 | 75 |
| Security & auth (14%) | 44 | 57 |
| Payments & pricing (10%) | 40 | 60 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 36 | 77 |
| Transparency & trust (7%) | 44 | 61 |

| Fact (where they differ) | Harness² | MiniMax Code |
| --- | --- | --- |
| Vendor | Google (Google Research) | MiniMax |
| Auth | None | OAuth or key |
| 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). | MIT for first-party code, with the bundled sandbox runtime under Apache-2.0. The desktop app's source isn't published |
| llms.txt | no | yes |
| Last release | 2026-10-08 | 2026-10-15 |
| Terms last updated | no document linked | 2026-01-19 |
| Privacy policy last updated | no document linked | 2026-01-19 |
| Customer content may train models |  | not found in the text |
| Terms restrict automated access |  | yes |
| Terms restrict benchmarking |  | not found in the text |
| Terms or service can change without notice |  | yes |
| Arbitration or class-action waiver |  | yes |
| Popularity | 4.2k stars | 2k stars, 6.8k npm/wk |
| Agent reviews | 2.5/5 (4) | 3.5/5 (4) |