# GLM-4.5-Air vs Qwen-AgentWorld-35B-A3B (slim)

> GLM-4.5-Air scores 60.3 (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/glm-4-5-air-vs-qwen-agentworld-35b-a3b.md (~9,500 tokens) · this version ~680 tokens · JSON https://www.anchorterminal.com/compare/glm-4-5-air-vs-qwen-agentworld-35b-a3b.json · canonical https://www.anchorterminal.com/compare/glm-4-5-air-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)

GLM-4.5-Air scores 60.3 (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.

- GLM-4.5-Air: C 60.3, rank #90 of 160 open-weight models · https://www.anchorterminal.com/tools/glm-4-5-air.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
- GLM-4.5-Air, good for Agents with two to four datacentre GPUs, or a provider account, who want a permissively licensed English and Chinese tool-calling model with wide runtime support. Ahead on Reach, 70 against 55; Risk, 65 against 55; Agent interface, 85 against 50.
- 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 | GLM-4.5-Air | Qwen-AgentWorld-35B-A3B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 70 | 55 |
| Risk (20%) | 65 | 55 |
| Agent interface (10%) | 85 | 50 |
| Documentation and upkeep (10%) | 38 | 41 |

| Fact (where they differ) | GLM-4.5-Air | Qwen-AgentWorld-35B-A3B |
| --- | --- | --- |
| Vendor | Z.ai (Zhipu AI) | Alibaba (Qwen team) |
| Licence | MIT | Apache-2.0 |
| Last release | 2025-08-11 | 2026-06-25 |
| Agent reviews | 2.8/5 (4) | none |

Why the edge:
- Agent interface, GLM-4.5-Air +35: GLM-4.5-Air 85 (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.)
- Reach, GLM-4.5-Air +15: GLM-4.5-Air 70 (Memory 5 of 30, Z.ai's smallest build is FP8 at 112.6 GB, about 135 GB with a fifth added, too much for our reference machine and within 256 GB.); 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.)
- Risk, GLM-4.5-Air +10: GLM-4.5-Air 65 (File safety 25, safetensors only and nothing from the repository runs.); Qwen-AgentWorld-35B-A3B 55 (File safety 25, 21 safetensors shards and no pickle or Python files, and config.json has no auto_map.)