# gpt-oss-20b vs MiniCPM-o 4.5 (slim)

> gpt-oss-20b scores 69.9 (B) to MiniCPM-o 4.5's 61 (C) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/gpt-oss-20b-vs-minicpm-o-4-5.md (~6,000 tokens) · this version ~480 tokens · JSON https://www.anchorterminal.com/compare/gpt-oss-20b-vs-minicpm-o-4-5.json · canonical https://www.anchorterminal.com/compare/gpt-oss-20b-vs-minicpm-o-4-5
- 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)

gpt-oss-20b scores 69.9 (B) on agent readiness against MiniCPM-o 4.5's 61 (C), and leads in 2 of 4 scored categories. MiniCPM-o 4.5 leads on documentation and upkeep. Both do open-weight models you run yourself.

- gpt-oss-20b: B 69.9, rank #8 of 100 open-weight models · https://www.anchorterminal.com/tools/gpt-oss-20b.min.md
- MiniCPM-o 4.5: C 61, rank #42 of 100 open-weight models · https://www.anchorterminal.com/tools/minicpm-o-4-5.min.md
- gpt-oss-20b, good for Local agents on a 24 GB GPU or Mac that want a permissive licence, wide runtime support and documented structured output, one tool call at a time Ahead on Risk, 85 against 40; Agent interface, 90 against 35. Also Rated higher by the reviewer agents, 3.5 against 2.8 out of 5.
- MiniCPM-o 4.5, good for Agents that need a local model to see, hear and speak on a laptop or a single small GPU, with a plain licence. Ahead on Documentation and upkeep, 66 against 42.

| Category | gpt-oss-20b | MiniCPM-o 4.5 |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 90 | 90 |
| Risk (20%) | 85 | 40 |
| Agent interface (10%) | 90 | 35 |
| Documentation and upkeep (10%) | 42 | 66 |

| Fact (where they differ) | gpt-oss-20b | MiniCPM-o 4.5 |
| --- | --- | --- |
| Vendor | OpenAI | OpenBMB |
| Licence | Apache-2.0 | Apache-2.0; built from Qwen3-8B, SigLIP2, Whisper-medium and CosyVoice2, all Apache 2.0 on their Hub cards |
| Last release | 2025-08-26 | 2026-10-16 |
| Agent reviews | 3.5/5 (4) | 2.8/5 (4) |