# GLM-5

GLM-5 is an AI model released by Z.ai on Feb 12 2026. It has 744B parameters and open weight. At release it scored 28% on BullshitBench v2, 86% on GPQA Diamond and 1435 on Arena Elo (Code).

## Facts

| Field | Value |
| --- | --- |
| Model | GLM-5 |
| Developer | Z.ai |
| Release date | Thursday, Feb 12 2026 |
| Licensing | Open Weight |
| Parameters | 744B |

## Benchmark scores published at release

| Benchmark | Score | What it measures |
| --- | --- | --- |
| BullshitBench v2 | 28% | Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. |
| SWE-Bench Verified | 77.8% | Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. |
| SWE-Bench Multilingual | 73.3% | Like SWE-Bench, but the coding problems span many programming languages, not just one. Tests how broadly the AI can code. Higher is better. |
| Terminal-Bench 2.0 | 56.2% | Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? (Version 2.0 of the test.) Higher is better. |
| BrowseComp | 75.9% | Can the AI browse the web and track down hard-to-find answers? Higher is better. |
| Humanity's Last Exam (with tools) | 50.4% | Humanity's Last Exam — extremely hard expert questions across many subjects. “With tools” means the AI is allowed to search the web or run code while answering. Higher is better. |
| GPQA Diamond | 86% | Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. |
| Arena Elo (Code) | 1435 | Like the text arena, but people vote on which AI writes better code. The votes become a chess-style Elo rating on arena.ai. Higher is better. |

## About GLM-5

GLM-5, released February 12, 2026, doubled Z.ai's flagship to 744B parameters while keeping the weights open. It scored 77.8% on SWE-Bench Verified, 86.0% on GPQA, and 75.9% on BrowseComp — at release the strongest agentic-research score of any open-weight model — with 50.4% on Humanity's Last Exam with tools.

Landing a week after Claude Opus 4.6 and GPT-5.3-Codex, GLM-5 kept open weights within striking distance of the closed frontier through early 2026. GLM-5.1 followed in April with a 200K context window, and GLM-5.2 pushed the family to a 1M-token context in June 2026.

## Questions and answers

### When was GLM-5 released?

GLM-5 was released by Z.ai on Thursday, Feb 12 2026.

### Who made GLM-5?

GLM-5 was built by Z.ai. Chinese AI lab spun out of Tsinghua University (formerly Zhipu AI), building the open-weight GLM family. Rebranded internationally as Z.ai in 2025.

### What benchmark scores did GLM-5 get?

GLM-5 reports 8 tracked benchmark scores — BullshitBench v2: 28%; SWE-Bench Verified: 77.8%; SWE-Bench Multilingual: 73.3%; Terminal-Bench 2.0: 56.2%; BrowseComp: 75.9%; Humanity's Last Exam (with tools): 50.4%; GPQA Diamond: 86%; Arena Elo (Code): 1435. Scores are the figures published at release by Z.ai.

### How many parameters does GLM-5 have?

GLM-5 is reported at 744B parameters.

### Is GLM-5 open source?

Partly. GLM-5 is an open-weight model: the trained weights are free to download and run locally or on your own infrastructure, but the training data and code are not fully released and the license may restrict some commercial uses. It is not open source in the strict sense.

### What came before and after GLM-5?

Z.ai's previous tracked release was GLM-4.7 on Dec 22 2025, 52 days earlier. It was followed by GLM-5.1 on Apr 7 2026.


---

Canonical page: https://aireleasetracker.com/model/zai/glm-5
Full dataset: https://aireleasetracker.com/llms-full.txt · JSON: https://aireleasetracker.com/models.json
Source: AI Release Tracker (https://aireleasetracker.com). Benchmark scores are the figures published by the releasing lab at launch.