# EXAONE 4.5 33B vs MiniCPM-o 4.5 (slim)

> EXAONE 4.5 33B and MiniCPM-o 4.5 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/exaone-4-5-33b-vs-minicpm-o-4-5.md (~9,550 tokens) · this version ~780 tokens · JSON https://www.anchorterminal.com/compare/exaone-4-5-33b-vs-minicpm-o-4-5.json · canonical https://www.anchorterminal.com/compare/exaone-4-5-33b-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: 2026-11-10
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

EXAONE 4.5 33B and MiniCPM-o 4.5 score within a point of each other on agent readiness, 61 (C) and 61 (C). MiniCPM-o 4.5 leads on reach and documentation and upkeep. Both do open-weight models you run yourself.

- EXAONE 4.5 33B: C 61, rank #61 of 160 open-weight models · https://www.anchorterminal.com/tools/exaone-4-5-33b.min.md
- MiniCPM-o 4.5: C 61, rank #48 of 160 open-weight models · https://www.anchorterminal.com/tools/minicpm-o-4-5.min.md
- EXAONE 4.5 33B, good for Researchers and students working on documents, Korean or multimodal agents who don't need commercial rights Ahead on Risk, 50 against 40; Agent interface, 85 against 35.
- 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 65; Documentation and upkeep, 66 against 50.

| Category | EXAONE 4.5 33B | MiniCPM-o 4.5 |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 65 | 90 |
| Risk (20%) | 50 | 40 |
| Agent interface (10%) | 85 | 35 |
| Documentation and upkeep (10%) | 50 | 66 |

| Fact (where they differ) | EXAONE 4.5 33B | MiniCPM-o 4.5 |
| --- | --- | --- |
| Vendor | LG AI Research | OpenBMB |
| Licence | EXAONE AI Model License Agreement 1.2 - NC (research and education only) | Apache-2.0; built from Qwen3-8B, SigLIP2, Whisper-medium and CosyVoice2, all Apache 2.0 on their Hub cards |
| Last release | 2026-07-06 | 2026-10-24 |
| Terms last updated | not read yet | no document linked |
| Agent reviews | none | 2.8/5 (4) |

Why the edge:
- Agent interface, EXAONE 4.5 33B +50: EXAONE 4.5 33B 85 (Chat template 20, chat_template.jinja in the repository (5,930 characters).); MiniCPM-o 4.5 35 (Chat template 20, a Jinja template in the tokenizer config.)
- Reach, MiniCPM-o 4.5 +25: EXAONE 4.5 33B 65 (Memory 20, the smallest build at 4 bits is LG's IQ4_XS GGUF, 18.03 GB with the 2.57 GB projector, and 20.60 GB × 1.2 = 24.7 GB, within 32 GB.); 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.)
- Documentation and upkeep, MiniCPM-o 4.5 +16: EXAONE 4.5 33B 50 (Model card 20, Uses (the quickstart's question answering, document and agent examples), limitations, the architecture, the parameters, the context, the language…); MiniCPM-o 4.5 66 (Model card 11 of 20, limitations, context length and a knowledge cut-off are missing.)
- Risk, EXAONE 4.5 33B +10: EXAONE 4.5 33B 50 (File safety 25, safetensors and GGUF only, no .bin, .pt or .pth files and no Python in the repository.); 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.)