Zhipu AI model product
GLM 4.7
7 is a coding-centric large language model from Zhipu AI with configurable reasoning and support for multi-step tool use.
Updated Oct 23, 2026. Default version: GLM-4.7
LLMBoard Score57.6GLM-4.7
Coverage100%13 benchmark families
Context window204.8KTokens
Official input price$0.4482Zhipu AI API
GLM 4.7 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
GLM 4.7 Benchmark Results
Benchmark scores for GLM-4.7.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkTau-bench | Score87.40% | Rank02 | Participants6 | Percentile80.00% | EvidenceC | Evaluated |
| BenchmarkBrowseComp-zh | Score66.60% | Rank06 | Participants15 | Percentile64.29% | EvidenceC | Evaluated |
| BenchmarkAA AIME 2025 | Score95.00% | Rank07 | Participants96 | Percentile93.68% | EvidenceB | EvaluatedN/A |
| BenchmarkIMO-AnswerBench | Score82.00% | Rank15 | Participants22 | Percentile33.33% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench v6 | Score84.90% | Rank16 | Participants67 | Percentile77.27% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench | Score33.30% | Rank16 | Participants25 | Percentile37.50% | EvidenceC | Evaluated |
| BenchmarkAIME 2025 | Score95.70% | Rank21 | Participants122 | Percentile83.47% | EvidenceC | Evaluated |
| BenchmarkMMLU-Pro | Score84.30% | Rank31 | Participants142 | Percentile78.72% | EvidenceC | Evaluated |
| BenchmarkHumanity's Last Exam | Score42.80% | Rank34 | Participants109 | Percentile69.44% | EvidenceC | Evaluated |
| BenchmarkSWE-bench Multilingual | Score66.70% | Rank34 | Participants50 | Percentile32.65% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Verified | Score73.80% | Rank46 | Participants120 | Percentile62.18% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 2.0 | Score41.00% | Rank46 | Participants53 | Percentile13.46% | EvidenceC | Evaluated |
| BenchmarkBrowseComp | Score52.00% | Rank50 | Participants70 | Percentile28.99% | EvidenceC | Evaluated |
| BenchmarkAA IFBench | Score67.89% | Rank56 | Participants168 | Percentile67.07% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Webdev | Score1,435.34 rating | Rank60 | Participants107 | Percentile44.34% | EvidenceA | Evaluated |
| BenchmarkAA GPQA Diamond | Score85.86% | Rank61 | Participants199 | Percentile69.70% | EvidenceB | EvaluatedN/A |
| BenchmarkGPQA | Score85.70% | Rank63 | Participants256 | Percentile75.69% | EvidenceC | Evaluated |
| BenchmarkAA Omniscience Accuracy | Score29.32% | Rank64 | Participants201 | Percentile68.50% | EvidenceB | EvaluatedN/A |
| BenchmarkAA HLE Text No Tools | Score27.39% | Rank64 | Participants200 | Percentile68.34% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Text Factuality | Score1,443.80 rating | Rank65 | Participants131 | Percentile50.77% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,435.34 rating | Rank66 | Participants218 | Percentile70.05% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,441.27 rating | Rank71 | Participants218 | Percentile67.74% | EvidenceA | Evaluated |
| BenchmarkAA CritPt | Score1.71% | Rank78 | Participants200 | Percentile61.31% | EvidenceB | EvaluatedN/A |
| BenchmarkAA LCR v1.1 | Score71.00% | Rank85 | Participants193 | Percentile56.25% | EvidenceB | EvaluatedN/A |
GLM 4.7 Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext style control | Categoryindustry medicine and healthcare | Rank29 | Rating / score1,487.13 | Votes826 | ObservationsN/A | Result date |
| Arenatext | Categoryjapanese | Rank30 | Rating / score1,438.66 | Votes125 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry medicine and healthcare | Rank31 | Rating / score1,468.70 | Votes826 | ObservationsN/A | Result date |
| Arenatext style control | Categoryjapanese | Rank37 | Rating / score1,439.20 | Votes125 | ObservationsN/A | Result date |
| Arenatext | Categorychinese | Rank47 | Rating / score1,494.62 | Votes1,022 | ObservationsN/A | Result date |
| Arenatext | Categoryenglish | Rank47 | Rating / score1,452.94 | Votes5,026 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry life and physical and social science | Rank49 | Rating / score1,457.29 | Votes2,139 | ObservationsN/A | Result date |
| Arenatext factuality | Categorychinese | Rank50 | Rating / score1,488.14 | Votes610 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry life and physical and social science | Rank52 | Rating / score1,472.74 | Votes2,139 | ObservationsN/A | Result date |
| Arenatext | Categorykorean | Rank53 | Rating / score1,399.04 | Votes177 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryenglish | Rank53 | Rating / score1,458.91 | Votes4,568 | ObservationsN/A | Result date |
| Arenatext style control | Categorychinese | Rank54 | Rating / score1,495.29 | Votes1,022 | ObservationsN/A | Result date |
| Arenatext | Categorymulti turn | Rank55 | Rating / score1,445.59 | Votes1,929 | ObservationsN/A | Result date |
| Arenatext | Categorypolish | Rank56 | Rating / score1,435.05 | Votes461 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev-html | Rank56 | Rating / score1,446.61 | Votes3,892 | ObservationsN/A | Result date |
| Arenatext style control | Categoryenglish | Rank58 | Rating / score1,461.62 | Votes5,026 | ObservationsN/A | Result date |
| Arenatext style control | Categorymulti turn | Rank58 | Rating / score1,457.08 | Votes1,929 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryexclude ties | Rank60 | Rating / score1,445.03 | Votes8,162 | ObservationsN/A | Result date |
| Arenatext factuality | Categorymulti turn | Rank60 | Rating / score1,454.09 | Votes1,340 | ObservationsN/A | Result date |
| Arenatext style control | Categorykorean | Rank60 | Rating / score1,402.63 | Votes177 | ObservationsN/A | Result date |
| Arenawebdev | Categoryoverall | Rank60 | Rating / score1,435.34 | Votes4,007 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev | Rank60 | Rating / score1,435.34 | Votes4,007 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev-react | Rank60 | Rating / score1,419.82 | Votes106 | ObservationsN/A | Result date |
| Arenatext | Categoryhard prompts english | Rank61 | Rating / score1,452.45 | Votes2,699 | ObservationsN/A | Result date |
| Arenatext | Categoryexclude ties | Rank62 | Rating / score1,430.87 | Votes8,495 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry legal and government | Rank62 | Rating / score1,444.39 | Votes969 | ObservationsN/A | Result date |
| Arenatext style control | Categoryhard prompts english | Rank62 | Rating / score1,473.56 | Votes2,699 | ObservationsN/A | Result date |
| Arenatext style control | Categoryspanish | Rank63 | Rating / score1,440.37 | Votes345 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry life and physical and social science | Rank64 | Rating / score1,462.92 | Votes1,421 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry business and management and financial operations | Rank65 | Rating / score1,429.21 | Votes2,293 | ObservationsN/A | Result date |
GLM 4.7 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $0.4482 input, $2.09 output per 1M
- Official provider
- Zhipu AI
- Lowest third-party
- From $0.274 input, $1.1 output per 1M via AIHubMix
- Tracked offerings
- 35
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderAlibaba Coding Plan (China) | Provider model IDglm-4.7 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context202.8K | Updated |
| ProviderZ.AI Coding Plan | Provider model IDglm-4.7 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context204.8K | Updated |
| ProviderAlibaba Coding Plan | Provider model IDglm-4.7 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context202.8K | Updated |
| ProviderKUAE Cloud Coding Plan | Provider model IDGLM-4.7 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context204.8K | Updated |
| ProviderAIHubMix | Provider model IDglm-4.7 | Regionglobal | Input / 1M$0.274 | Output / 1M$1.1 | Context200K | Updated |
| Provider302.AI | Provider model IDglm-4.7 | Regionglobal | Input / 1M$0.286 | Output / 1M$1.14 | Context204.8K | Updated |
| ProviderZenMux | Provider model IDz-ai/glm-4.7 | Regionglobal | Input / 1M$0.2911 | Output / 1M$1.16 | Context200K | Updated |
| ProviderMeganova | Provider model IDzai-org/GLM-4.7 | Regionglobal | Input / 1M$0.40 | Output / 1M$1.75 | Context202.8K | Updated |
| ProviderDeep Infra | Provider model IDzai-org/GLM-4.7 | Regionglobal | Input / 1M$0.40 | Output / 1M$1.75 | Context202.8K | Updated |
| ProviderOfox | Provider model IDz-ai/glm-4.7 | Regionglobal | Input / 1M$0.40 | Output / 1M$2.2 | Context204.8K | Updated |
| ProviderNanoGPT | Provider model IDz-ai/glm-4.7 | Regionglobal | Input / 1M$0.4004 | Output / 1M$1.93 | Context200K | Updated |
| ProviderMoark | Provider model IDGLM-4.7 | Regionglobal | Input / 1M$0.42 | Output / 1M$2.2 | Context204.8K | Updated |
| ProviderZhipu AI | Provider model IDglm-4.7 | Regionglobal | Input / 1M$0.4482 | Output / 1M$2.09 | Context204.8K | Updated |
| ProviderDInference | Provider model IDglm-4.7 | Regionglobal | Input / 1M$0.45 | Output / 1M$1.65 | Context200K | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDglm-4.7 | Regionglobal | Input / 1M$0.45 | Output / 1M$2 | Context204.8K | Updated |
| ProviderCrossModel | Provider model IDz-ai/glm-4.7 | Regionglobal | Input / 1M$0.47 | Output / 1M$2.16 | Context200K | Updated |
| ProviderOpenRouter | Provider model IDz-ai/glm-4.7 | Regionglobal | Input / 1M$0.54 | Output / 1M$1.98 | Context204.8K | Updated |
| ProviderKilo Gateway | Provider model IDz-ai/glm-4.7 | Regionglobal | Input / 1M$0.54 | Output / 1M$1.98 | Context204.8K | Updated |
| ProviderVenice AI | Provider model IDzai-org-glm-4.7 | Regionglobal | Input / 1M$0.55 | Output / 1M$2.65 | Context198K | Updated |
| ProviderOrcaRouter | Provider model IDz-ai/glm-4.7 | Regionglobal | Input / 1M$0.60 | Output / 1M$2.2 | Context204.8K | Updated |
| ProviderVertex | Provider model IDzai-org/glm-4.7-maas | Regionglobal | Input / 1M$0.60 | Output / 1M$2.2 | Context200K | Updated |
| ProviderHugging Face | Provider model IDzai-org/GLM-4.7 | Regionglobal | Input / 1M$0.60 | Output / 1M$2.2 | Context204.8K | Updated |
| ProviderImpossibl | Provider model IDzai/glm-4.7 | Regionglobal | Input / 1M$0.60 | Output / 1M$2.2 | Context204.8K | Updated |
| ProviderJiekou.AI | Provider model IDzai-org/glm-4.7 | Regionglobal | Input / 1M$0.60 | Output / 1M$2.2 | Context204.8K | Updated |
| ProviderZ.AI | Provider model IDglm-4.7 | Regionglobal | Input / 1M$0.60 | Output / 1M$2.2 | Context204.8K | Updated |
| ProviderAmazon Bedrock | Provider model IDzai.glm-4.7 | Regionglobal | Input / 1M$0.60 | Output / 1M$2.2 | Context202.8K | Updated |
| ProviderMerge Gateway | Provider model IDzai/glm-4.7 | Regionglobal | Input / 1M$0.60 | Output / 1M$2.2 | Context200K | Updated |
| ProviderOpenCode | Provider model IDglm-4.7 | Regionglobal | Input / 1M$0.60 | Output / 1M$2.2 | Context204.8K | Updated |
| ProviderBaseten | Provider model IDzai-org/GLM-4.7 | Regionglobal | Input / 1M$0.60 | Output / 1M$2.2 | Context200K | Updated |
| ProviderVercel AI Gateway | Provider model IDzai/glm-4.7 | Regionglobal | Input / 1M$0.60 | Output / 1M$2.2 | Context200K | Updated |
GLM 4.7 Runtime Performance
Provider-specific output speed and catalog latency for GLM-4.7. Runtime does not affect the capability score.
No runtime data
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
GLM 4.7 Specifications
Technical details for the model's default version.
- Version
- GLM-4.7
- Released
- Dec 22, 2025
- Knowledge cutoff
- Unknown
- Parameters
- 358B
- Context window
- 204.8K
- Max output
- 202.8K
- Inputs
- text
- Outputs
- text
- Open weights
- Yes
- License
- MIT
GLM 4.7 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-4.7 | Released | LLMBoard57.61 | Parameters358B | Context204.8K | Max output202.8K | Open weightsYes | LicenseMIT |
Models similar to GLM 4.7
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
ZA
GLM 5V Turbo
Zhipu AI
ZA
GLM 4.6
Zhipu AI
ZA
GLM 5
Zhipu AI
ZA
GLM 5.1
Zhipu AI
ZA
GLM 4.5
Zhipu AI
ZA
GLM 4.5 Air
Zhipu AI
What is GLM 4.7?
Key information about GLM 4.7 and its available data.
7 is a coding-centric model from Zhipu AI that can preserve reasoning across turns and lets users control thinking per request. ai API, popular coding agents, and public weights on HuggingFace and ModelScope for local use with vLLM or SGLang.
Data as of 2026-10-22.
FAQ
Common questions about GLM 4.7.
When was GLM 4.7 released?
GLM 4.7's default version was released on Dec 22, 2025.
How much does GLM 4.7 cost?
GLM 4.7's official API price is $0.4482 per million input tokens and $2.09 per million output tokens via Zhipu AI. The lowest tracked third-party offer starts at $0.274 input and $1.1 output via AIHubMix.
Who created GLM 4.7?
GLM 4.7 was created by Zhipu AI.
What is the context window for GLM 4.7?
The default version has a 204.8K token context window.
Is GLM 4.7 open weight?
Yes. The default version is marked as open weight under MIT.
How many API providers offer GLM 4.7?
35 provider offerings are linked to the default version.