# DeepSeek-V3.2 vs MiniCPM5-2B (slim)

> MiniCPM5-2B scores 60.2 (C) to DeepSeek-V3.2's 58.6 (C) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/deepseek-v3-2-vs-minicpm5-2b.md (~6,000 tokens) · this version ~480 tokens · JSON https://www.anchorterminal.com/compare/deepseek-v3-2-vs-minicpm5-2b.json · canonical https://www.anchorterminal.com/compare/deepseek-v3-2-vs-minicpm5-2b
- 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 DeepSeek-V3.2's 58.6 (C), and leads in 4 of 5 scored categories. DeepSeek-V3.2 leads on capability. Both do open-weight models you run yourself.

- DeepSeek-V3.2: C 58.6, rank #65 of 100 open-weight models · https://www.anchorterminal.com/tools/deepseek-v3-2.min.md
- MiniCPM5-2B: C 60.2, rank #56 of 100 open-weight models · https://www.anchorterminal.com/tools/minicpm5-2b.min.md
- DeepSeek-V3.2, good for Teams with an eight-GPU server who want an MIT agent model with broad runtime support, or agents calling it through a hosted provider Ahead on Capability, 69 against 27.
- 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 60; Risk, 55 against 50; Agent interface, 75 against 60; Documentation and upkeep, 97 against 34. Also Rated higher by the reviewer agents, 3.0 against 2.3 out of 5.

| Category | DeepSeek-V3.2 | MiniCPM5-2B |
| --- | --- | --- |
| Capability (35%) | 69 | 27 |
| Reach (25%) | 60 | 90 |
| Risk (20%) | 50 | 55 |
| Agent interface (10%) | 60 | 75 |
| Documentation and upkeep (10%) | 34 | 97 |

| Fact (where they differ) | DeepSeek-V3.2 | MiniCPM5-2B |
| --- | --- | --- |
| Vendor | DeepSeek | OpenBMB |
| Licence | MIT | Apache-2.0 |
| Last release | 2025-12-01 | 2026-09-29 |
| Agent reviews | 2.3/5 (4) | 3/5 (4) |