Zhipu AI model product
GLM 5
GLM 5 is a Zhipu AI LLM for complex system engineering and long-range Agent tasks, with a 744B-parameter Mixture of Experts architecture and a 200K context length.
Updated Sep 8, 2026. Default version: GLM-5
LLMBoard Score65.8GLM-5
Coverage0%5 benchmark families
Context window200KTokens
Official input price$1Zhipu AI API
GLM 5 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
GLM 5 Benchmark Results
Benchmark scores for GLM-5.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| Benchmarkt2-bench | Score89.70% | Rank03 | Participants23 | Percentile90.91% | EvidenceC | Evaluated |
| BenchmarkMCP Atlas | Score67.80% | Rank23 | Participants34 | Percentile33.33% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Verified | Score77.80% | Rank24 | Participants113 | Percentile79.46% | EvidenceC | Evaluated |
| BenchmarkBrowseComp | Score75.90% | Rank27 | Participants63 | Percentile58.06% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 2.0 | Score56.20% | Rank29 | Participants51 | Percentile44.00% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text | Score1,446.36 rating | Rank40 | Participants210 | Percentile81.34% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Factuality | Score1,451.88 rating | Rank41 | Participants121 | Percentile66.67% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,457.77 rating | Rank41 | Participants210 | Percentile80.86% | EvidenceA | Evaluated |
| BenchmarkLM Arena Webdev | Score1,435.72 rating | Rank51 | Participants97 | Percentile47.92% | EvidenceA | Evaluated |
GLM 5 Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext factuality | Categorychinese | Rank12 | Rating / score1,524.10 | Votes1,245 | ObservationsN/A | Result date |
| Arenatext | Categorykorean | Rank23 | Rating / score1,423.70 | Votes538 | ObservationsN/A | Result date |
| Arenatext | Categorychinese | Rank25 | Rating / score1,510.40 | Votes1,740 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry mathematical | Rank27 | Rating / score1,460.38 | Votes1,069 | ObservationsN/A | Result date |
| Arenatext style control | Categorychinese | Rank27 | Rating / score1,515.18 | Votes1,740 | ObservationsN/A | Result date |
| Arenatext style control | Categorycreative writing | Rank27 | Rating / score1,448.14 | Votes4,500 | ObservationsN/A | Result date |
| Arenatext style control | Categorykorean | Rank27 | Rating / score1,427.16 | Votes538 | ObservationsN/A | Result date |
| Arenatext | Categoryenglish | Rank29 | Rating / score1,459.35 | Votes12,319 | ObservationsN/A | Result date |
| Arenatext factuality | Categorycreative writing | Rank29 | Rating / score1,443.56 | Votes3,337 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry entertainment and sports and media | Rank30 | Rating / score1,438.10 | Votes4,273 | ObservationsN/A | Result date |
| Arenatext factuality | Categorymath | Rank30 | Rating / score1,455.25 | Votes1,172 | ObservationsN/A | Result date |
| Arenatext | Categorycreative writing | Rank32 | Rating / score1,438.30 | Votes4,500 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry legal and government | Rank32 | Rating / score1,469.06 | Votes1,560 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry writing and literature and language | Rank33 | Rating / score1,448.22 | Votes5,166 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry writing and literature and language | Rank34 | Rating / score1,438.95 | Votes6,559 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry entertainment and sports and media | Rank34 | Rating / score1,438.94 | Votes5,499 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry entertainment and sports and media | Rank35 | Rating / score1,427.11 | Votes5,499 | ObservationsN/A | Result date |
| Arenatext | Categorymulti turn | Rank35 | Rating / score1,457.66 | Votes4,424 | ObservationsN/A | Result date |
| Arenatext | Categoryspanish | Rank35 | Rating / score1,451.92 | Votes1,121 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryenglish | Rank35 | Rating / score1,466.15 | Votes12,022 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry business and management and financial operations | Rank35 | Rating / score1,457.40 | Votes4,292 | ObservationsN/A | Result date |
| Arenatext style control | Categoryenglish | Rank35 | Rating / score1,473.35 | Votes12,319 | ObservationsN/A | Result date |
| Arenatext style control | Categorymulti turn | Rank35 | Rating / score1,473.16 | Votes4,424 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry medicine and healthcare | Rank36 | Rating / score1,478.51 | Votes1,482 | ObservationsN/A | Result date |
| Arenatext factuality | Categorylonger query | Rank36 | Rating / score1,468.71 | Votes8,854 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry writing and literature and language | Rank36 | Rating / score1,449.86 | Votes6,559 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryhard prompts english | Rank37 | Rating / score1,485.81 | Votes6,476 | ObservationsN/A | Result date |
| Arenatext style control | Categoryspanish | Rank37 | Rating / score1,455.93 | Votes1,121 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry life and physical and social science | Rank38 | Rating / score1,474.81 | Votes3,284 | ObservationsN/A | Result date |
| Arenatext style control | Categoryhard prompts english | Rank38 | Rating / score1,488.41 | Votes7,881 | ObservationsN/A | Result date |
GLM 5 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $1 input, $3.2 output per 1M
- Official provider
- Zhipu AI
- Lowest third-party
- From $0.50 input, $2.55 output per 1M via NanoGPT
- Tracked offerings
- 43
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderAlibaba Token Plan | Provider model IDglm-5 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context202.8K | Updated |
| ProviderAlibaba Coding Plan (China) | Provider model IDglm-5 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context202.8K | Updated |
| ProviderAlibaba Coding Plan | Provider model IDglm-5 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context202.8K | Updated |
| ProviderTencent Coding Plan (China) | Provider model IDglm-5 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context202.8K | Updated |
| ProviderSCNet Token Plan | Provider model IDGLM-5 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context204.8K | Updated |
| ProviderAlibaba Token Plan (China) | Provider model IDglm-5 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context202.8K | Updated |
| ProviderNanoGPT | Provider model IDz-ai/glm-5 | Regionglobal | Input / 1M$0.50 | Output / 1M$2.55 | Context200K | Updated |
| ProviderAlibaba (China) | Provider model IDglm-5 | Regionglobal | Input / 1M$0.573 | Output / 1M$2.58 | Context202.8K | Updated |
| ProviderZenMux | Provider model IDz-ai/glm-5 | Regionglobal | Input / 1M$0.58 | Output / 1M$2.6 | Context200K | Updated |
| ProviderDeep Infra | Provider model IDzai-org/GLM-5 | Regionglobal | Input / 1M$0.60 | Output / 1M$2.08 | Context202.8K | Updated |
| ProviderOpenRouter | Provider model IDz-ai/glm-5 | Regionglobal | Input / 1M$0.60 | Output / 1M$1.92 | Context204.8K | Updated |
| ProviderCrossModel | Provider model IDz-ai/glm-5 | Regionglobal | Input / 1M$0.60 | Output / 1M$3 | Context200K | Updated |
| ProviderGMI Cloud | Provider model IDzai-org/GLM-5-FP8 | Regionglobal | Input / 1M$0.60 | Output / 1M$1.92 | Context202.8K | Updated |
| Provider302.AI | Provider model IDglm-5 | Regionglobal | Input / 1M$0.60 | Output / 1M$2.6 | Context204.8K | Updated |
| ProviderKilo Gateway | Provider model IDz-ai/glm-5 | Regionglobal | Input / 1M$0.60 | Output / 1M$1.92 | Context198K | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDglm-5 | Regionglobal | Input / 1M$0.72 | Output / 1M$2.3 | Context203K | Updated |
| ProviderDInference | Provider model IDglm-5 | Regionglobal | Input / 1M$0.75 | Output / 1M$2.4 | Context200K | Updated |
| ProviderMeganova | Provider model IDzai-org/GLM-5 | Regionglobal | Input / 1M$0.80 | Output / 1M$2.56 | Context202.8K | Updated |
| ProviderCharm Hyper | Provider model IDglm-5 | Regionglobal | Input / 1M$0.86 | Output / 1M$2.78 | Context202.8K | Updated |
| ProviderTokenGo | Provider model IDz-ai/glm-5 | Regionglobal | Input / 1M$0.89 | Output / 1M$3.26 | Context204.8K | Updated |
| ProviderFastRouter | Provider model IDz-ai/glm-5 | Regionglobal | Input / 1M$0.95 | Output / 1M$3.15 | Context204.8K | Updated |
| ProviderBaseten | Provider model IDzai-org/GLM-5 | Regionglobal | Input / 1M$0.95 | Output / 1M$3.15 | Context202.8K | Updated |
| ProviderCortecs | Provider model IDglm-5 | Regionglobal | Input / 1M$0.988 | Output / 1M$3.16 | Context202.8K | Updated |
| ProviderOrcaRouter | Provider model IDz-ai/glm-5 | Regionglobal | Input / 1M$1 | Output / 1M$3.2 | Context204.8K | Updated |
| ProviderVertex | Provider model IDzai-org/glm-5-maas | Regionglobal | Input / 1M$1 | Output / 1M$3.2 | Context202.8K | Updated |
| ProviderHugging Face | Provider model IDzai-org/GLM-5 | Regionglobal | Input / 1M$1 | Output / 1M$3.2 | Context202.8K | Updated |
| ProviderImpossibl | Provider model IDzai/glm-5 | Regionglobal | Input / 1M$1 | Output / 1M$3.2 | Context204.8K | Updated |
| ProviderZ.AI | Provider model IDglm-5 | Regionglobal | Input / 1M$1 | Output / 1M$3.2 | Context204.8K | Updated |
| ProviderAmazon Bedrock | Provider model IDzai.glm-5 | Regionglobal | Input / 1M$1 | Output / 1M$3.2 | Context202.8K | Updated |
| ProviderOpenCode Go | Provider model IDglm-5 | Regionglobal | Input / 1M$1 | Output / 1M$3.2 | Context202.8K | Updated |
GLM 5 Runtime Performance
Provider-specific output speed and catalog latency for GLM-5. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderZAI | Output Speed30.00 tok/s | Catalog Latency3.00 s | Max Input200K | Max Output128K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
GLM 5 Specifications
Technical details for the model's default version.
- Version
- GLM-5
- Released
- Feb 11, 2026
- Knowledge cutoff
- Unknown
- Parameters
- 744B
- Context window
- 200K
- Max output
- 128K
- Inputs
- text
- Outputs
- text
- Open weights
- No
- License
- MIT
GLM 5 Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionGLM-5 | Released | LLMBoard65.85 | Parameters744B | Context200K | Max output128K | Open weightsNo | LicenseMIT |
Models similar to GLM 5
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
ZA
GLM 5.1
Zhipu AI
ZA
GLM 4.7
Zhipu AI
ZA
GLM 5.2
Zhipu AI
ZA
GLM 5V Turbo
Zhipu AI
ZA
GLM 4.6
Zhipu AI
ZA
GLM 4.5
Zhipu AI
What is GLM 5?
Key information about GLM 5 and its available data.
5T tokens. It uses DeepSeek Sparse Attention and supports thinking modes, real-time streaming, function calling, context caching, structured output, and up to 128K max output tokens.
Data as of 2026-09-08.
FAQ
Common questions about GLM 5.
When was GLM 5 released?
GLM 5's default version was released on Feb 11, 2026.
How much does GLM 5 cost?
GLM 5's official API price is $1 per million input tokens and $3.2 per million output tokens via Zhipu AI. The lowest tracked third-party offer starts at $0.50 input and $2.55 output via NanoGPT.
Who created GLM 5?
GLM 5 was created by Zhipu AI.
What is the context window for GLM 5?
The default version has a 200K token context window.
Is GLM 5 open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer GLM 5?
43 provider offerings are linked to the default version.