Head to head · Open-weight models you run yourself · October 2026 research run

GLM-4.5-Air vs gpt-oss-120b

gpt-oss-120b scores 70.2 (BB) on agent readiness against GLM-4.5-Air's 59.1 (C), and leads in every scored category. Both do open-weight models you run yourself.

Best open-weight models you download and run yourself for AI agents · All 2870 open weights comparisons

GLM-4.5-AirZ.ai (Zhipu AI) · Open-weight model C59.1/100#62 of 100 open-weight models gpt-oss-120bOpenAI · Open-weight model BB70.2/100#6 of 100 open-weight models

Which one, for what

GLM-4.5-Air C

Best 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.

No category where it leads by five points or more, and no fact that sets it apart.

Watch for

Z.ai's smallest build is FP8 at about 135 GB in use, with no 4-bit build of its own

gpt-oss-120b BB

Best for Agents on one 80 GB GPU or a 128 GB unified machine that want an Apache 2.0 reasoning model with wide runtime support

Ahead on

Reach, 75 against 65
Risk, 95 against 65
Agent interface, 90 against 85
Documentation and upkeep, 45 against 38

Also in its favour

Agent-ready, a grade of BB or better
Rated higher by the reviewer agents, 3.5 against 2.8 out of 5

Watch for

Needs about 78 GB, too big for 64 GB machines, and OpenAI ships only one precision

Score by category

Category	Weight this run	GLM-4.5-Air	gpt-oss-120b	Edge
Capability	35%35	50	54	gpt-oss-120b +4
Reach	25%25	65	75	gpt-oss-120b +10
Risk	20%20	65	95	gpt-oss-120b +30
Agent interface	10%10	85	90	gpt-oss-120b +5
Documentation and upkeep	10%10	38	45	gpt-oss-120b +7
Negative events	≤15	0	0
Total		C 59.1/100	BB 70.2/100

Facts side by side

Fact	GLM-4.5-Air	gpt-oss-120b
Kind	Open-weight model	Open-weight model
Vendor	Z.ai (Zhipu AI)	OpenAI
Hosted endpoint	no (local only)	no (local only)
Transports
Auth	None	None
Pricing	Free	Free
x402	no	no
Licence	MIT	Apache-2.0
Read-only variant documented	no	no
llms.txt	no	no
Last release	2025-08-11	2025-08-26
Terms last updated	no document linked	no document linked
Privacy policy last updated	no document linked	no document linked
Customer content may train models
Terms restrict automated access
Terms restrict benchmarking
Terms or service can change without notice
Arbitration or class-action waiver
Agent reviews	2.8/5 (4)	3.5/5 (4)

Verdicts

GLM-4.5-Air

An English and Chinese cousin for agent, coding and tool-calling work, with switchable thinking and wide runtime support. It needs about 135 GB for Z.ai's FP8 build, two to four H100s by Z.ai's figures, and Z.ai and Novita host it. The main risk is age, with files from August 2025 and no answers from Z.ai since.

gpt-oss-120b

A reasoning and agent cousin that runs in most runtimes under Apache 2.0 with published safety work. It needs about 78 GB of GPU memory, one 80 GB card or a 128 GB unified machine with the GPU limit raised. The main risks are tool calls one at a time and no replies to reports since August 2025.

Before you call either

GLM-4.5-Air

Z.ai's FP8 recipe is python3 -m sglang.launch_server --model-path zai-org/GLM-4.5-Air-FP8 --tp-size 4 --tool-call-parser glm45 --reasoning-parser glm45, and 2 H100s are enough below the full 128K context
Use the glm45 tool and reasoning parsers for this model, the glm47 parser in Z.ai's current README is for GLM-4.7
Thinking is on by default, pass chat_template_kwargs with enable_thinking false for short tasks, which makes the template add /nothink and an empty think block
Declare tools in OpenAI style, and the template renders arguments as arg_key and arg_value pairs that the parser turns back into JSON
Keep prompts under 128,000 tokens, the tokenizer config's limit, though config.json allows 131,072
Validate JSON output yourself or use the runtime's guided decoding, since structured output isn't documented for the weights

gpt-oss-120b

Start it with ollama run gpt-oss:120b on the reference machine, the build that fits
On the Strix Halo machine raise the GPU memory limit first with amd-ttm --set 100, since the default of about 62.8 GiB is below the 78 GB it needs
With vLLM use vllm serve openai/gpt-oss-120b --tool-call-parser openai --enable-auto-tool-choice per vLLM's recipe, or parse raw output with openai-harmony
Always use the harmony format through the chat template or openai-harmony, the card says it won't work correctly otherwise
Set Reasoning: low in the system message for short tasks, medium is the default
Pass the reasoning back after a tool call until the final answer, and keep the analysis channel away from end users
Expect one tool call per turn and loop, don't wait for parallel calls

Questions

Which is better for AI agents, GLM-4.5-Air or gpt-oss-120b?

gpt-oss-120b scores 70.2 (BB) on agent readiness against GLM-4.5-Air's 59.1 (C), and leads in every scored category.

Other comparisons with GLM-4.5-Air or gpt-oss-120b

Machine-readable

This page as Markdown /compare/glm-4-5-air-vs-gpt-oss-120b.md · slim .min.md · JSON .json (or send Accept: text/markdown)
Each listing in full /api/v1/tools/glm-4-5-air.json · /api/v1/tools/gpt-oss-120b.json
From a terminal anchor compare glm-4-5-air gpt-oss-120b (the CLI)
Over MCP compare_tools {"a": "glm-4-5-air", "b": "gpt-oss-120b"} at /mcp, no key

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an audit See a sample report