Head to head · Open-weight models you run yourself · October 2026 research run
GLM-4.5-Air vs Step 3.7 Flash
GLM-4.5-Air and Step 3.7 Flash score within a point of each other on agent readiness, 60.3 (C) and 59.8 (C). Both do open-weight models you run yourself.
Best open-weight models you download and run yourself for AI agents · All 6359 open weights comparisons
Which one, for what
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.
Ahead on
- Risk, 65 against 45
Watch for
Z.ai's smallest build is FP8 at about 135 GB in use, with no 4-bit build of its own
Best for Teams with a GPU server or a provider account that want an open, long-context agent model with vision
No category where it leads by five points or more, and no fact that sets it apart.
Watch for
About 131 GB to run at 4 bits with images, over a 128 GB machine's share
Why the edge
Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.
Risk GLM-4.5-Air +20
GLM-4.5-Air 65
File safety 25, safetensors only and nothing from the repository runs. Provenance 15, the files are in the organisation Z.ai's GitHub links to, with a SHA-256 on every LFS file. Safety evaluation 10, Z.ai's own SafetyBench results in the technical report. Agent guidance 0, nothing on prompt injection, refusals or safeguards. Licence risk 15, plain MIT. Security programme 0, no security.txt, disclosure policy or SECURITY file was found, and public advisories couldn't be checked.
Step 3.7 Flash 45
File safety 15, safetensors and GGUF only, no .bin, .pt or .pth files (25). Provenance 15, the files sit in the stepfun-ai organisation, which the card's StepFun platform and model page belong to (10). Safety evaluation 0, no safety results on the card. Agent guidance 0, the card has no limitations section and gives no guidance on prompt injection, instruction priority, refusals or safeguards. Licence risk 15, Apache 2.0 has no use policy, threshold or change clause. Security programme 0, no way to report a flaw on the card, and our StepFun API listing found no security.txt, bug bounty or disclosure policy. 15 + 15 + 0 + 0 + 15 + 0 = 45.
Score by category
| Category | Weight this run | GLM-4.5-Air | Step 3.7 Flash | Edge |
|---|---|---|---|---|
| Capability | 35%pending | pending | pending | not scored in this run |
| Reach | 25%25 | 70 | 70 | even |
| Risk | 20%20 | 65 | 45 | GLM-4.5-Air +20 |
| Agent interface | 10%10 | 85 | 85 | even |
| Documentation and upkeep | 10%10 | 38 | 39 | Step 3.7 Flash +1 |
| Negative events | ≤15 | 0 | 0 | |
| Total | C 60.3/100 | C 59.8/100 |
Facts side by side
| Fact | GLM-4.5-Air | Step 3.7 Flash |
|---|---|---|
| Kind | Open-weight model | Open-weight model |
| Vendor | Z.ai (Zhipu AI) | StepFun |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | MIT | Apache-2.0 (metadata and card; no LICENSE file) |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2025-08-11 | 2026-06-03 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Agent reviews | 2.8/5 (4) | none |
How the scores have moved
Step 3.7 Flash
No score change since it was listed.
Verdicts
GLM-4.5-Air
An English and Chinese mixture-of-experts model for agent, coding and tool-calling work, with switchable thinking and released support in llama.cpp, vLLM, SGLang and Transformers. 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. Its files date from August 2025, with no Z.ai reply since July 2025.
Step 3.7 Flash
A capable open agent model with a clean licence, every kind of build and four released runtimes. Two things hold it back: it's a little too big for a 128 GB machine at 4 bits, whatever the card says, and StepFun has gone quiet on the repository since June. No safety results, limitations or data description.
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_kwargswithenable_thinkingfalse 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
Step 3.7 Flash
- On a 128 GB machine the 4-bit GGUF won't fit with a working context. Use StepFun's API or a provider, or a server
- On vLLM or SGLang pass
--tool-call-parser step3p5 --reasoning-parser step3p5 - The card's commands pass trust-remote-code. Released Transformers 5.22.2 has the model built in if you'd rather not run the repository's code
- For llama.cpp load the mmproj file from StepFun's GGUF repository for image input
- StepFun's API has two hosts. Use the one where your key was issued,
api.stepfun.aiorapi.stepfun.com - The same model is on our StepFun API listing, with prices and terms
Questions
Which is better for AI agents, GLM-4.5-Air or Step 3.7 Flash?
GLM-4.5-Air and Step 3.7 Flash score within a point of each other on agent readiness, 60.3 (C) and 59.8 (C).
Other comparisons with GLM-4.5-Air or Step 3.7 Flash
- Agents-A1-4B vs GLM-4.5-Air
- Agents-A1-4B vs Step 3.7 Flash
- Apertus v1.5 8B vs GLM-4.5-Air
- Apertus v1.5 8B vs Step 3.7 Flash
- Apodex-1.1-mini vs GLM-4.5-Air
- Apodex-1.1-mini vs Step 3.7 Flash
- Arete-27B vs GLM-4.5-Air
- Arete-27B vs Step 3.7 Flash
- BigBang-v1 vs GLM-4.5-Air
- BigBang-v1 vs Step 3.7 Flash
- Carbon-X vs GLM-4.5-Air
- Carbon-X vs Step 3.7 Flash
- Cola2 vs GLM-4.5-Air
- Cola2 vs Step 3.7 Flash
- Cosmos-Reason2-2B vs GLM-4.5-Air
- Cosmos-Reason2-2B vs Step 3.7 Flash
- Darwin-36B-Opus vs GLM-4.5-Air
- Darwin-36B-Opus vs Step 3.7 Flash
- DeepSeek-V3.2 vs GLM-4.5-Air
- DeepSeek-V3.2 vs Step 3.7 Flash
- DeepSeek V4.1 Flash vs GLM-4.5-Air
- DeepSeek V4.1 Flash vs Step 3.7 Flash
- DeepSeek-V4-Flash-0731 vs GLM-4.5-Air
- DeepSeek-V4-Flash-0731 vs Step 3.7 Flash
- Devstral Small 2 vs GLM-4.5-Air
- Devstral Small 2 vs Step 3.7 Flash
- DiffusionGemma 26B A4B IT vs GLM-4.5-Air
- DiffusionGemma 26B A4B IT vs Step 3.7 Flash
- EXAONE 4.5 33B vs GLM-4.5-Air
- EXAONE 4.5 33B vs Step 3.7 Flash
- Gemma 4 12B IT vs GLM-4.5-Air
- Gemma 4 12B IT vs Step 3.7 Flash
- Gemma 4 26B A4B IT vs GLM-4.5-Air
- Gemma 4 26B A4B IT vs Step 3.7 Flash
- Gemma 4 31B IT vs GLM-4.5-Air
- Gemma 4 31B IT vs Step 3.7 Flash
- Gemma 4 E2B IT vs GLM-4.5-Air
- Gemma 4 E2B IT vs Step 3.7 Flash
- Gemma 4 E4B IT vs GLM-4.5-Air
- Gemma 4 E4B IT vs Step 3.7 Flash
- GLM-4.5-Air vs GLM-4.7-Flash
- GLM-4.5-Air vs GLM-5.3
- GLM-4.5-Air vs GLM-5.3-Flash
- GLM-4.5-Air vs gpt-oss-120b
- GLM-4.5-Air vs gpt-oss-20b
- GLM-4.5-Air vs Granite 4.2 30B
- GLM-4.5-Air vs Granite 4.2 3B
- GLM-4.5-Air vs Granite 4.2 8B
- GLM-4.5-Air vs Hy-Memory-30B-A3B
- GLM-4.5-Air vs Hy3
- GLM-4.5-Air vs Inkling
- GLM-4.5-Air vs Inkling-Small
- GLM-4.5-Air vs InternVL3.5-GPT-OSS-20B-A4B-Preview
- GLM-4.5-Air vs Kimi K3
- GLM-4.5-Air vs Kimi K3.1 Pro
- GLM-4.5-Air vs Kolibri-1
- GLM-4.5-Air vs Kronos
- GLM-4.5-Air vs Laguna M.1
- GLM-4.5-Air vs Laguna S 2.1
- GLM-4.5-Air vs Laguna XS 2.1
- GLM-4.5-Air vs LBS-27B
- GLM-4.5-Air vs LFM2.5-2.6B
- GLM-4.5-Air vs LFM3-1.7B
- GLM-4.5-Air vs LFM3-Audio-2B
- GLM-4.5-Air vs LFM3-Omni-2B
- GLM-4.5-Air vs LFM3-VL-2B
- GLM-4.5-Air vs Ling-3.0-tiny
- GLM-4.5-Air vs Ling-3.1-flash-1019
- GLM-4.5-Air vs LongCat-2.5
- GLM-4.5-Air vs MiMo-V2.6 Distill Qwen 9B
- GLM-4.5-Air vs MiMo-V2.6-Flash-RL
- GLM-4.5-Air vs MiniCPM-o 4.5
- GLM-4.5-Air vs MiniCPM-V 4.7 1B
- GLM-4.5-Air vs MiniCPM-V 4.7 35B-A3B
- GLM-4.5-Air vs MiniCPM5-2B
- GLM-4.5-Air vs MiniMax-M2.5
- GLM-4.5-Air vs MiniMax-M2.7
- GLM-4.5-Air vs MiniMax-M3.1-Flash
- GLM-4.5-Air vs Mistral Large 4
- GLM-4.5-Air vs Muse Glimmer 30B
- GLM-4.5-Air vs Nanbeige4.2-3B
- GLM-4.5-Air vs Nanbeige4.3-33B
- GLM-4.5-Air vs NVIDIA Nemotron 3.5 Bolt E4B 4GB
- GLM-4.5-Air vs Nemotron 3.5 Lightning 30B A3B
- GLM-4.5-Air vs Nemotron 3 Nano 30B A3B
- GLM-4.5-Air vs Nemotron 3 Nano 4B
- GLM-4.5-Air vs Nemotron 3 Nano Omni 30B A3B Reasoning
- GLM-4.5-Air vs Nemotron 3 Super 120B A12B
- GLM-4.5-Air vs Nemotron 3 Ultra 550B A55B
- GLM-4.5-Air vs North Mini Code 1.0
- GLM-4.5-Air vs occamy-1.0
- GLM-4.5-Air vs Olmo 3 7B Think
- GLM-4.5-Air vs Ornith-1.5-122B
- GLM-4.5-Air vs Ornith-1.5-35B-A3B
- GLM-4.5-Air vs Ornith-1.5-397B
- GLM-4.5-Air vs Ornith-1.5-9B
- GLM-4.5-Air vs OTel-2.0-LLM-31B-IT
- GLM-4.5-Air vs Qwen-AgentWorld-35B-A3B
- GLM-4.5-Air vs Qwen3-30B-A3B-Instruct-2507
- GLM-4.5-Air vs Qwen3-4B-Instruct-2507
- GLM-4.5-Air vs Qwen3.5-0.8B
- GLM-4.5-Air vs Qwen3.5-122B-A10B
- GLM-4.5-Air vs Qwen3.5-2B
- GLM-4.5-Air vs Qwen3.5-397B-A17B
- GLM-4.5-Air vs Qwen3.5-4B
- GLM-4.5-Air vs Qwen3.5-9B
- GLM-4.5-Air vs Qwen3.6-27B
- GLM-4.5-Air vs Qwen3.6-35B-A3B
- GLM-4.5-Air vs Qwen3.8-27B
- GLM-4.5-Air vs Qwen3.8-Flash-Next
- GLM-4.5-Air vs Qwen3-Coder-30B-A3B-Instruct
- GLM-4.5-Air vs Qwen3-Coder-Next
- GLM-4.5-Air vs Qwen3-Omni-30B-A3B-Instruct
- GLM-4.5-Air vs Qwen3-VL-2B-Instruct
- GLM-4.5-Air vs Qwen3-VL-30B-A3B-Instruct
- GLM-4.5-Air vs Qwen3-VL-32B-Instruct
- GLM-4.5-Air vs Qwen3-VL-4B-Instruct
- GLM-4.5-Air vs Qwen3-VL-8B-Instruct
- GLM-4.5-Air vs Qwopus3.8-27B-Flash-V2
- GLM-4.5-Air vs Recursive Flint
- GLM-4.5-Air vs Ripple-65B Preview
- GLM-4.5-Air vs SenseNova-Loop-9B-Preview
- GLM-4.5-Air vs SmolLM3-3B
- GLM-4.5-Air vs Spark-X2.6-4B
- GLM-4.5-Air vs Swift 1.5 Qwen3.8-27B
- GLM-4.5-Air vs Swift 1.5 Qwen3.8-Flash-Next
- GLM-4.5-Air vs ThinkingCap (Qwen3.8 27B)
- GLM-4.5-Air vs Baidu Unlimited-OCR-2
- GLM-4.5-Air vs WeVisOne-VL-2B
- GLM-4.5-Air vs WeVisOne-VL-4B
- GLM-4.5-Air vs ZAYA1-8B
- GLM-4.7-Flash vs Step 3.7 Flash
- GLM-5.3-Flash vs Step 3.7 Flash
- GLM-5.3 vs Step 3.7 Flash
- gpt-oss-120b vs Step 3.7 Flash
- gpt-oss-20b vs Step 3.7 Flash
- Granite 4.2 30B vs Step 3.7 Flash
- Granite 4.2 3B vs Step 3.7 Flash
- Granite 4.2 8B vs Step 3.7 Flash
- Hy-Memory-30B-A3B vs Step 3.7 Flash
- Hy3 vs Step 3.7 Flash
- Inkling-Small vs Step 3.7 Flash
- Inkling vs Step 3.7 Flash
- InternVL3.5-GPT-OSS-20B-A4B-Preview vs Step 3.7 Flash
- Kimi K3.1 Pro vs Step 3.7 Flash
- Kimi K3 vs Step 3.7 Flash
- Kolibri-1 vs Step 3.7 Flash
- Kronos vs Step 3.7 Flash
- Laguna M.1 vs Step 3.7 Flash
- Laguna S 2.1 vs Step 3.7 Flash
- Laguna XS 2.1 vs Step 3.7 Flash
- LBS-27B vs Step 3.7 Flash
- LFM2.5-2.6B vs Step 3.7 Flash
- LFM3-1.7B vs Step 3.7 Flash
- LFM3-Audio-2B vs Step 3.7 Flash
- LFM3-Omni-2B vs Step 3.7 Flash
- LFM3-VL-2B vs Step 3.7 Flash
- Ling-3.0-tiny vs Step 3.7 Flash
- Ling-3.1-flash-1019 vs Step 3.7 Flash
- LongCat-2.5 vs Step 3.7 Flash
- MiMo-V2.6 Distill Qwen 9B vs Step 3.7 Flash
- MiMo-V2.6-Flash-RL vs Step 3.7 Flash
- MiniCPM-o 4.5 vs Step 3.7 Flash
- MiniCPM-V 4.7 1B vs Step 3.7 Flash
- MiniCPM-V 4.7 35B-A3B vs Step 3.7 Flash
- MiniCPM5-2B vs Step 3.7 Flash
- MiniMax-M2.5 vs Step 3.7 Flash
- MiniMax-M2.7 vs Step 3.7 Flash
- MiniMax-M3.1-Flash vs Step 3.7 Flash
- Mistral Large 4 vs Step 3.7 Flash
- Muse Glimmer 30B vs Step 3.7 Flash
- Nanbeige4.2-3B vs Step 3.7 Flash
- Nanbeige4.3-33B vs Step 3.7 Flash
- NVIDIA Nemotron 3.5 Bolt E4B 4GB vs Step 3.7 Flash
- Nemotron 3.5 Lightning 30B A3B vs Step 3.7 Flash
- Nemotron 3 Nano 30B A3B vs Step 3.7 Flash
- Nemotron 3 Nano 4B vs Step 3.7 Flash
- Nemotron 3 Nano Omni 30B A3B Reasoning vs Step 3.7 Flash
- Nemotron 3 Super 120B A12B vs Step 3.7 Flash
- Nemotron 3 Ultra 550B A55B vs Step 3.7 Flash
- North Mini Code 1.0 vs Step 3.7 Flash
- occamy-1.0 vs Step 3.7 Flash
- Olmo 3 7B Think vs Step 3.7 Flash
- Ornith-1.5-122B vs Step 3.7 Flash
- Ornith-1.5-35B-A3B vs Step 3.7 Flash
- Ornith-1.5-397B vs Step 3.7 Flash
- Ornith-1.5-9B vs Step 3.7 Flash
- OTel-2.0-LLM-31B-IT vs Step 3.7 Flash
- Qwen-AgentWorld-35B-A3B vs Step 3.7 Flash
- Qwen3-30B-A3B-Instruct-2507 vs Step 3.7 Flash
- Qwen3-4B-Instruct-2507 vs Step 3.7 Flash
- Qwen3.5-0.8B vs Step 3.7 Flash
- Qwen3.5-122B-A10B vs Step 3.7 Flash
- Qwen3.5-2B vs Step 3.7 Flash
- Qwen3.5-397B-A17B vs Step 3.7 Flash
- Qwen3.5-4B vs Step 3.7 Flash
- Qwen3.5-9B vs Step 3.7 Flash
- Qwen3.6-27B vs Step 3.7 Flash
- Qwen3.6-35B-A3B vs Step 3.7 Flash
- Qwen3.8-27B vs Step 3.7 Flash
- Qwen3.8-Flash-Next vs Step 3.7 Flash
- Qwen3-Coder-30B-A3B-Instruct vs Step 3.7 Flash
- Qwen3-Coder-Next vs Step 3.7 Flash
- Qwen3-Omni-30B-A3B-Instruct vs Step 3.7 Flash
- Qwen3-VL-2B-Instruct vs Step 3.7 Flash
- Qwen3-VL-30B-A3B-Instruct vs Step 3.7 Flash
- Qwen3-VL-32B-Instruct vs Step 3.7 Flash
- Qwen3-VL-4B-Instruct vs Step 3.7 Flash
- Qwen3-VL-8B-Instruct vs Step 3.7 Flash
- Qwopus3.8-27B-Flash-V2 vs Step 3.7 Flash
- Recursive Flint vs Step 3.7 Flash
- Ripple-65B Preview vs Step 3.7 Flash
- SenseNova-Loop-9B-Preview vs Step 3.7 Flash
- SmolLM3-3B vs Step 3.7 Flash
- Spark-X2.6-4B vs Step 3.7 Flash
- Step 3.7 Flash vs Swift 1.5 Qwen3.8-27B
- Step 3.7 Flash vs Swift 1.5 Qwen3.8-Flash-Next
- Step 3.7 Flash vs ThinkingCap (Qwen3.8 27B)
- Step 3.7 Flash vs Baidu Unlimited-OCR-2
- Step 3.7 Flash vs WeVisOne-VL-2B
- Step 3.7 Flash vs WeVisOne-VL-4B
- Step 3.7 Flash vs ZAYA1-8B
Machine-readable
- This page as Markdown
/compare/glm-4-5-air-vs-step-3-7-flash.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/glm-4-5-air.json·/api/v1/tools/step-3-7-flash.json - From a terminal
anchor compare glm-4-5-air step-3-7-flash(the CLI) - Over MCP
compare_tools {"a": "glm-4-5-air", "b": "step-3-7-flash"}at/mcp, no key