# MiniCPM5-2B vs Qwen-AgentWorld-35B-A3B (slim)

> MiniCPM5-2B scores 59.7 (C) to Qwen-AgentWorld-35B-A3B's 52.1 (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-qwen-agentworld-35b-a3b.md (~9,650 tokens) · this version ~630 tokens · JSON https://www.anchorterminal.com/compare/minicpm5-2b-vs-qwen-agentworld-35b-a3b.json · canonical https://www.anchorterminal.com/compare/minicpm5-2b-vs-qwen-agentworld-35b-a3b
- 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)

MiniCPM5-2B scores 59.7 (C) on agent readiness against Qwen-AgentWorld-35B-A3B's 52.1 (D), and leads in 3 of 4 scored categories. Both do open-weight models you run yourself.

- MiniCPM5-2B: C 59.7, rank #94 of 160 open-weight models · https://www.anchorterminal.com/tools/minicpm5-2b.min.md
- Qwen-AgentWorld-35B-A3B: D 52.1, rank #141 of 160 open-weight models · https://www.anchorterminal.com/tools/qwen-agentworld-35b-a3b.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 55; Agent interface, 75 against 50; Documentation and upkeep, 92 against 41.
- Qwen-AgentWorld-35B-A3B, good for Agent builders who want to train or test an agent against simulated tools, terminals, browsers and phones on a 128 GB machine

| Category | MiniCPM5-2B | Qwen-AgentWorld-35B-A3B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 90 | 55 |
| Risk (20%) | 55 | 55 |
| Agent interface (10%) | 75 | 50 |
| Documentation and upkeep (10%) | 92 | 41 |

| Fact (where they differ) | MiniCPM5-2B | Qwen-AgentWorld-35B-A3B |
| --- | --- | --- |
| Vendor | OpenBMB | Alibaba (Qwen team) |
| Last release | 2026-09-29 | 2026-06-25 |
| Agent reviews | 3/5 (4) | none |

Why the edge:
- Documentation and upkeep, MiniCPM5-2B +51: MiniCPM5-2B 92 (Model card 17, everything but a knowledge cut-off.); Qwen-AgentWorld-35B-A3B 41 (Model card 11, the card gives intended use (simulating agent environments), architecture, parameters and context length.)
- Reach, MiniCPM5-2B +35: MiniCPM5-2B 90 (Memory 30, OpenBMB's own MLX 4-bit build is 1.42 GB and its Q4_K_M GGUF 1.56 GB, about 2 GB with the fifth added.); Qwen-AgentWorld-35B-A3B 55 (Memory 10, Alibaba's only build is the BF16 safetensors, 69.32 GB, and 69.32 GB × 1.2 = 83.2 GB, above 64 GB and inside the reference machine's GPU share.)
- Agent interface, MiniCPM5-2B +25: MiniCPM5-2B 75 (Chat template 20, a Jinja file in the repository.); Qwen-AgentWorld-35B-A3B 50 (Chat template 20, chat_template.jinja in the repository, the same as the template in tokenizer_config.json.)