# MiniCPM-o 4.5 vs Ornith-1.5-122B (slim)

> MiniCPM-o 4.5 and Ornith-1.5-122B score within a point of each other for open-weight models you run yourself, 61 and 61 out of 100. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/minicpm-o-4-5-vs-ornith-1-5-122b.md (~9,400 tokens) · this version ~780 tokens · JSON https://www.anchorterminal.com/compare/minicpm-o-4-5-vs-ornith-1-5-122b.json · canonical https://www.anchorterminal.com/compare/minicpm-o-4-5-vs-ornith-1-5-122b
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-10
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

MiniCPM-o 4.5 and Ornith-1.5-122B score within a point of each other on agent readiness, 61 (C) and 61 (C). Ornith-1.5-122B leads on risk and agent interface. Both do open-weight models you run yourself.

- MiniCPM-o 4.5: C 61, rank #48 of 160 open-weight models · https://www.anchorterminal.com/tools/minicpm-o-4-5.min.md
- Ornith-1.5-122B: C 61, rank #81 of 160 open-weight models · https://www.anchorterminal.com/tools/ornith-1-5-122b.min.md
- 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 Reach, 90 against 75; Documentation and upkeep, 66 against 36.
- Ornith-1.5-122B, good for Local coding and terminal agents on a 128 GB unified-memory machine or a 96 GB GPU setup, where a clear licence file and an answering publisher aren't required Ahead on Risk, 50 against 40; Agent interface, 85 against 35.

| Category | MiniCPM-o 4.5 | Ornith-1.5-122B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 90 | 75 |
| Risk (20%) | 40 | 50 |
| Agent interface (10%) | 35 | 85 |
| Documentation and upkeep (10%) | 66 | 36 |

| Fact (where they differ) | MiniCPM-o 4.5 | Ornith-1.5-122B |
| --- | --- | --- |
| Vendor | OpenBMB | Ornith |
| Licence | Apache-2.0; built from Qwen3-8B, SigLIP2, Whisper-medium and CosyVoice2, all Apache 2.0 on their Hub cards | MIT |
| Agent reviews | 2.8/5 (4) | none |

Why the edge:
- Agent interface, Ornith-1.5-122B +50: MiniCPM-o 4.5 35 (Chat template 20, a Jinja template in the tokenizer config.); Ornith-1.5-122B 85 (Chat template 20, a Jinja file in the repository.)
- Documentation and upkeep, MiniCPM-o 4.5 +30: MiniCPM-o 4.5 66 (Model card 11 of 20, limitations, context length and a knowledge cut-off are missing.); Ornith-1.5-122B 36 (Model card 11, it covers intended use, architecture, parameters and context but not limitations, languages or a knowledge cut-off.)
- Reach, MiniCPM-o 4.5 +15: MiniCPM-o 4.5 90 (Memory 30, OpenBMB's 4-bit GGUF with its vision file is 5.9 GB, about 7 GB with a fifth added.); Ornith-1.5-122B 75 (Memory 10, since Ornith's own MLX 4-bit build is 69.7 GB and needs about 83.6 GB with the fifth added, over 64 GB and inside the reference machine's 107.4 GB, a…)
- Risk, Ornith-1.5-122B +10: MiniCPM-o 4.5 40 (File safety 5 of 25, two pickle files sit in the speech stage and the documented load runs repository code.); Ornith-1.5-122B 50 (File safety 25, safetensors and GGUF only and no Python in any of Ornith's repositories for this size, so the card's --trust-remote-code flag loads nothing from…)