When was GLM-5 released?

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

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.

How much does GLM-5 cost?

GLM-5 costs $1.00 per million input tokens and $3.20 per million output tokens through the Z.ai API. Cached input is $0.20 per million tokens. Rates are pay-as-you-go API prices verified against Z.ai's published pricing on August 18, 2026.

What benchmark scores did GLM-5 get?

GLM-5 reports 7 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%. Tracked scores may come from lab reports or independent benchmarks; source details accompany the benchmark data.

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.

GLM-5Open Weight

Released Feb 12 2026

GLM-5 is an AI model released by Z.ai on Thursday, Feb 12 2026, 52 days after GLM-4.7. It is an open-weight model — the trained weights are available to download and run. It is a 744B parameter model. Benchmark results (shown below) cover BullshitBench v2, SWE-Bench Verified, SWE-Bench Multilingual, Terminal-Bench 2.0, BrowseComp, Humanity's Last Exam, and 1 more.

API pricing

Input: $1.00
Cached input: $0.20
Output: $3.20

Reasoning or thinking is supported.

USD per 1M tokens

Available from


GMICloud	$0.60	$1.92	200K	fp8
StreamLake	$0.60	$1.92	200K	fp8
Baidu	$0.70	$2.24	200K	fp8
SiliconFlow	$0.95	$2.55	200K	fp8
Amazon Bedrock	$1.00	$3.20	200K	—
Novita	$1.00	$3.20	200K	fp8
Venice	$1.00	$3.20	200K	fp8
Z.AI	$1.00	$3.20	200K	fp8

USD per 1M tokens

Benchmarks

Coding

SWE-Bench Verified

77.8%

#19 of 57

SWE-Bench Multilingual

73.3%

#11 of 14

Terminal & CLI

Terminal-Bench 2.0

56.2%

#10 of 14

Agentic & tool use

BrowseComp

75.9%

#21 of 28

Reasoning & science

Humanity's Last Exam

50.4%with tools

#23 of 44

GPQA Diamond

86%

#29 of 59

Robustness

BullshitBench v2

28%

#54 of 82

Compare GLM-5 with

GLM-5

Suggested comparisons

GLM-5vsGLM-5.3-Flash GLM-5vsGPT-6 Sol GLM-5vsClaude Opus 5.5 GLM-5vsGemini 3.8 Flash GLM-5vsMuse Spark 1.3 GLM-5vsGrok 4.7 GLM-5vsDeepSeek-V4.1-Flash GLM-5vsMistral Medium 3.5 GLM-5vsKimi K3 GLM-5vsQwen3.8-Max-0902 GLM-5vsNemotron 3.5 Lightning

About

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.

Frequently asked questions

: GLM-5 was released by Z.ai on Thursday, Feb 12 2026.
: 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.
: GLM-5 costs $1.00 per million input tokens and $3.20 per million output tokens through the Z.ai API. Cached input is $0.20 per million tokens. Rates are pay-as-you-go API prices verified against Z.ai's published pricing on August 18, 2026.
: GLM-5 reports 7 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%. Tracked scores may come from lab reports or independent benchmarks; source details accompany the benchmark data.
: GLM-5 is reported at 744B parameters.
: 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.
: 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.