GLM-5 — The GLM Model That Started the 5 Series

GLM-5 is the release that opened the current generation of the GLM model family. It arrived with materially stronger coding fundamentals than the 4.x line, more reliable multi-step execution, and noticeably better behaviour on complex agent tasks where a plan has to survive contact with real tool output. Everything the 5 series is now known for — long-horizon reasoning, agentic engineering, open weights under MIT — starts here.

Because the model authors publish their full comparison table for GLM-5.2 and GLM-5.1 only, GLM-5 has no benchmark column of its own. This page is honest about that: it gives you the spec sheet and positioning that were published, plus the nearest published reference column, rather than inventing numbers. If you need hard scores to make a decision, the flagship page is the right place to look.

5
series generation
the base the 5.1 and 5.2 releases were built on
MIT
open-source license
MIT, with no regional restrictions
Open
weights
published on HuggingFace and ModelScope

Free AI Playground — Try a Live Open-Source LLM

No sign-up, no account, no credits. Type a prompt and get a streamed answer.

Response will stream here...

This playground runs a free open-source LLM via OpenRouter. It is not GLM-5.2 and does not use GLM weights — it's here so you can test a live model while you read the published GLM benchmark data below.

What GLM-5 Changed for the GLM Model Family

The step from the 4.x line to GLM-5 was about reliability rather than headline capability. Multi-step execution is the part of agentic work that quietly decides whether a run finishes: a model that reasons beautifully but drops a step, forgets a constraint or re-does work it already completed will not survive a fifty-turn trajectory. GLM-5 tightened that behaviour, and it did so alongside better coding and better handling of complex agent tasks, which is why the two releases that followed could focus on horizon length rather than basic dependability. Read the 5 series as three moves: GLM-5 made long trajectories reliable, GLM-5.1 made them long, and GLM-5.2 made them very long by rebuilding the attention stack around a shared indexer.

Family
GLM-5 series
License
MIT open source
Positioning
General reasoning model
Succeeded by
GLM-5.1 · GLM-5.2
Weights host
HuggingFace · ModelScope

GLM-5 in the Published Benchmark Data

The published comparison table covers GLM-5.2 and GLM-5.1. The column below is GLM-5.1's — the closest published reference point to the GLM-5 generation. No benchmark column has been published for GLM-5 itself, and none is invented here.

Treat the column above as an upper-bound sanity check rather than a score for GLM-5. It shows where the generation immediately after GLM-5 landed: 95.3 on AIME 2026, 86.2 on GPQA-Diamond, 71.8 on MCP-Atlas and 58.4 on SWE-bench Pro, with long-horizon rows still weak. If you are choosing between GLM models on the basis of measured performance, the only two options with published columns are GLM-5.2 and GLM-5.1, and GLM-5.2 wins every row of that head-to-head.

See all 17 GLM benchmarks in detail →

How the 5 Series Compares

Comparison on Terminal-Bench 2.1 (Terminus-2), as published by the model authors.

The chart tracks the 5-series trajectory against the open-weight field on Terminal-Bench 2.1: GLM-5.1 at 63.5 and MiniMax M3 at 65.0 sit in the same band, Qwen3.7-Max reaches 75.0, and GLM-5.2 breaks out at 81.0. GLM-5 predates all of these measurements, so its place on that curve is inferred from positioning rather than measured — another reason to move to the flagship page if you need a number you can defend in a design review.

Read the full GLM-5.2 vs GLM-5.1 comparison →

Where GLM-5 Sits in the GLM Model Lineup

GLM-5 follows GLM-4.7 and precedes GLM-5-Turbo, GLM-5.1 and GLM-5.2. Its direct descendant in spirit is GLM-5-Turbo, which took the same base and tuned it for dynamic, long-chain agent scenarios. For production work today the family points you at GLM-5.2; GLM-5 matters mostly as the point where the current generation's design decisions were set.

More GLM Models

View all

GLM-5 FAQ

What is the GLM-5 model?
GLM-5 is the open-weight GLM model that opened the 5 series. It brought stronger coding, more reliable multi-step execution and better complex agent behaviour to the family, and it is the base that GLM-5-Turbo, GLM-5.1 and GLM-5.2 were built on. Like every core GLM model it ships under an MIT license.
What are GLM-5's benchmark scores?
The model authors have not published a benchmark column for GLM-5. Their comparison table covers GLM-5.2 and GLM-5.1 only, so this site does not quote scores for GLM-5. If you need published numbers, use the GLM-5.2 or GLM-5.1 pages, where every figure is a result reported by the model authors.
Should I use GLM-5 or GLM-5.2?
For almost any new project, GLM-5.2. It has a published 1M-token context, explicit effort levels, the IndexShare attention rebuild and a full benchmark column you can check. GLM-5 is worth considering only if you already have a working deployment on it and no reason to migrate.
Is GLM-5 open source?
Yes. GLM-5 is an MIT-licensed open-weight GLM model with weights published on HuggingFace and ModelScope, and no regional restrictions. You can serve it locally through the standard open inference stack, including transformers, vLLM and SGLang.
Is upgrading from GLM-5 to GLM-5.2 disruptive?
The main changes to plan for are the far larger context window, which shifts your serving bottleneck to KV-cache capacity, and the new effort levels, which add a per-request knob you did not previously have. Both are additive: existing prompts keep working, and you opt in to the longer window and the higher effort levels where they help.

Try a Live AI Model Free — No Account Needed

Read the GLM model benchmarks, then put a real model to work. The playground above is free and needs nothing from you; if you want a fuller AI toolkit, our partner's free tier starts here.