# MiniCPM5-2B vs Qwen3.5-2B (slim)

> MiniCPM5-2B scores 60.2 (C) to Qwen3.5-2B's 50.5 (D) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/minicpm5-2b-vs-qwen3-5-2b.md (~5,850 tokens) · this version ~380 tokens · JSON https://www.anchorterminal.com/compare/minicpm5-2b-vs-qwen3-5-2b.json · canonical https://www.anchorterminal.com/compare/minicpm5-2b-vs-qwen3-5-2b
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-10-21
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

MiniCPM5-2B scores 60.2 (C) on agent readiness against Qwen3.5-2B's 50.5 (D), and leads in 3 of 5 scored categories. Both do open-weight models you run yourself.

- MiniCPM5-2B: C 60.2, rank #56 of 100 open-weight models · https://www.anchorterminal.com/tools/minicpm5-2b.min.md
- Qwen3.5-2B: D 50.5, rank #92 of 100 open-weight models · https://www.anchorterminal.com/tools/qwen3-5-2b.min.md
- MiniCPM5-2B, good for On-device and laptop agents that want a 2 GB tool-calling helper with long context and open training data Ahead on Reach, 90 against 80; Agent interface, 75 against 60; Documentation and upkeep, 97 against 37.
- Qwen3.5-2B, good for Builders who want a cheap local helper or fine-tuning base for narrow tasks and image reading on a laptop, small GPU or CPU

| Category | MiniCPM5-2B | Qwen3.5-2B |
| --- | --- | --- |
| Capability (35%) | 27 | 28 |
| Reach (25%) | 90 | 80 |
| Risk (20%) | 55 | 55 |
| Agent interface (10%) | 75 | 60 |
| Documentation and upkeep (10%) | 97 | 37 |

| Fact (where they differ) | MiniCPM5-2B | Qwen3.5-2B |
| --- | --- | --- |
| Vendor | OpenBMB | Alibaba (Qwen team) |
| Last release | 2026-09-29 | 2026-03-02 |