DataLearner logo
GL

GLM 5.1

Reasoning modelGLMGLM-5

GLM 5.1

Release date: 2026-03-27Updated: 2026-08-23Views: 11,666
Live demoGitHubHugging FaceCompare
Parameters
754B
Context length
200K
Multilingual
Supported
Reasoning ability
4/5

GLM 5.1 is a reasoning model from Zhipu AI, released on 2026-03-27. It accepts text input and returns text output. The cataloged parameter count is 75.4B, with 4B active parameters per inference. The recorded context window is 200K, and the recorded maximum output is 125K. Cataloged capabilities include Reasoning model and Multilingual. The checkpoint is listed under the MIT license, with the license link included in the model references. Use the linked references to confirm current access, licensing, and provider-specific limits.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

GLM 5.1

Model basics

Reasoning traces
Supported
Thinking modes
Thinking Mode (Default)Standard Mode
Context length
200K tokens
Max output length
125K tokens
Model type
Reasoning model
Modality (in / out)
Text → Text
Release date
2026-03-27
Model file size
1.51TB
MoE architecture
Yes
Total params / Active params
754B / 40B
Knowledge cutoff
No data
GLM 5.1

Open source & experience

Code license
MIT License
Weights license
MIT License- Commercial use permitted
GitHub repo
github.com/zai-org/GLM-5.1
Hugging Face
huggingface.co/zai-org/GLM-5.1
Live demo
docs.z.ai/guides/llm/glm-5.1
GLM 5.1

Official resources

Paper
Paper
DataLearnerAI blog
N/A
GLM 5.1

API details

API speed
3/5
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Learn about pricing modes
Standard
TypeConditionInputOutput
Text-$1.40/ 1M$4.40/ 1M
Cache PricingPrompt Cache
TypeTTLWriteRead
Text5m$0.260/ 1M$4.40/ 1M

“—” means the modality is not billed in that direction, or the vendor has not published a price for it.

GLM 5.1

Benchmark Results

GLM 5.1 currently shows benchmark results led by HLE (27 / 197, score 52.30), AIME 2026 (4 / 21, score 95.30), Terminal Bench 2.0 (13 / 48, score 63.50). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.

Thinking
Tool usage
Internet

General Knowledge

3 evaluations
Benchmark / mode
Score
Rank/total
LiveBench
Standard Mode
70.18
37 / 117
HLE
Thinking Mode
31
101 / 197
HLE
Thinking ModeTools
52.30
27 / 197

General Evaluation

1 evaluations
Benchmark / mode
Score
Rank/total
GPQA Diamond
Thinking Mode
86.20
92 / 274

Writing and Creative Capabilities

1 evaluations
Benchmark / mode
Score
Rank/total
Creative Writing
Standard Mode
1589.20
40 / 106

Common Sense Reasoning

1 evaluations
Benchmark / mode
Score
Rank/total
SimpleBench
Standard Mode
55.10
42 / 94

Coding and Software Engineer

3 evaluations
Benchmark / mode
Score
Rank/total
Text Arena (Coding)
Standard Mode
1534
13 / 35
SWE-Bench Pro - Public
Thinking ModeTools
58.40
20 / 62
WeirdML v2
Standard ModeTools
57.10
32 / 52

AI Agent - Information Search

1 evaluations
Benchmark / mode
Score
Rank/total
BrowseComp
Thinking ModeToolsInternet
79.30
19 / 57

AI Agent - Tool Usage

5 evaluations
Benchmark / mode
Score
Rank/total
MCP-Atlas
Standard ModeTools
75.60
21 / 41
Terminal Bench 2.0
Thinking ModeTools
63.50
13 / 48
Terminal-Bench 2.1
HighTools
58.70
46 / 53
Terminal-Bench 2.1
MaxTools
58.70
46 / 53
Tool Decathlon
Thinking ModeTools
40.70
6 / 10

Text Embedding

2 evaluations
Benchmark / mode
Score
Rank/total
Context Arena
Standard Mode
30.29
116 / 126
Context Arena
Thinking Mode
62.05
74 / 126

Math and Reasoning

2 evaluations
Benchmark / mode
Score
Rank/total
AIME 2026
Thinking Mode
95.30
4 / 21
IMO-AnswerBench
Thinking Mode
83.80
14 / 24
View benchmark analysisCompare with other models

Compare with other models

GLM 5.1

Publisher

GLM 5.1

Model Overview

GLM 5.1 is a reasoning model from Zhipu AI, released on 2026-03-27.

It accepts text input and produces text output. Its cataloged capabilities include Reasoning model and Multilingual. The cataloged parameter count is 75.4B, with 4B active parameters per inference. The recorded context window is 200K, and the recorded maximum output is 125K.

The checkpoint is listed under the MIT license, with the license link included in the model references. The page records 4 API pricing rules from the listed provider; current provider pricing and conditions should be checked before deployment. The evaluation section contains 12 cataloged benchmark results with their recorded modes and scores. The page links 4 release, model-card, repository, or provider references for checking the underlying claims. Specifications, availability, and prices can change; undisclosed values are intentionally left unstated.

GLM 5.1

FAQ

What is GLM 5.1?

GLM 5.1 is a reasoning model from Zhipu AI, released on 2026-03-27. It accepts text input and returns text output. The cataloged parameter count is 75.4B, with 4B active parameters per inference. The recorded context window is 200K, and the recorded maximum output is 125K. Cataloged capabilities include Reasoning model and Multilingual. The checkpoint is listed under the MIT license, with the license link included in the model references. Use the linked references to confirm current access, licensing, and provider-specific limits.

What input and output modalities does GLM 5.1 support?

The current model record lists text as input and text as output.

What are the main recorded specifications for GLM 5.1?

The cataloged parameter count is 75.4B, with 4B active parameters per inference. The recorded context window is 200K, and the recorded maximum output is 125K. Fields without a source-backed value remain undisclosed.

Does GLM 5.1 have API pricing?

The page records 4 API pricing rules from the listed provider; current provider pricing and conditions should be checked before deployment.

Are benchmark results available for GLM 5.1?

The evaluation section contains 12 cataloged benchmark results with their recorded modes and scores. Compare only results that use the same benchmark version and evaluation mode.

Is GLM 5.1 open source?

The checkpoint is listed under the MIT license, with the license link included in the model references. Review the linked license text before commercial or derivative use.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code