Zhipu AI model product
GLM 5.2
2 is an open-source large language model from Zhipu AI with a 1M-token input context and 128K maximum output.
Updated Oct 23, 2026. Default version: GLM-5.2
LLMBoard Score75.8GLM-5.2
Coverage100%19 benchmark families
Context window1MTokens
Official input price$1.2Zhipu AI API
GLM 5.2 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
GLM 5.2 Benchmark Results
Benchmark scores for GLM-5.2.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkAIME 2026 | Score99.20% | Rank01 | Participants27 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkCritPT | Score16.70% | Rank02 | Participants7 | Percentile83.33% | EvidenceC | Evaluated |
| BenchmarkIMO-AnswerBench | Score91.00% | Rank02 | Participants22 | Percentile95.24% | EvidenceC | Evaluated |
| BenchmarkLM Arena Agent Tool Hallucination | Score0.69% | Rank02 | Participants44 | Percentile97.67% | EvidenceA | Evaluated |
| BenchmarkProgram Bench | Score63.70% | Rank05 | Participants18 | Percentile76.47% | EvidenceC | Evaluated |
| BenchmarkFrontierSWE | Score74.00% | Rank06 | Participants17 | Percentile68.75% | EvidenceB | Evaluated |
| BenchmarkHMMT Feb 26 | Score92.50% | Rank06 | Participants13 | Percentile58.33% | EvidenceC | Evaluated |
| BenchmarkPostTrainBench | Score34.30% | Rank07 | Participants9 | Percentile25.00% | EvidenceC | Evaluated |
| BenchmarkLM Arena Agent Praise Complaint | Score5.54% | Rank08 | Participants44 | Percentile83.72% | EvidenceA | Evaluated |
| BenchmarkHMMT 2025 | Score94.40% | Rank09 | Participants33 | Percentile75.00% | EvidenceC | Evaluated |
| BenchmarkDeepSWE | Score46.20% | Rank10 | Participants13 | Percentile25.00% | EvidenceC | Evaluated |
| BenchmarkSWE-Marathon | Score13.00% | Rank10 | Participants10 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkNL2Repo | Score48.90% | Rank11 | Participants25 | Percentile58.33% | EvidenceC | Evaluated |
| BenchmarkAA CritPt | Score20.86% | Rank12 | Participants200 | Percentile94.47% | EvidenceB | EvaluatedN/A |
| BenchmarkMCP Atlas | Score76.80% | Rank13 | Participants39 | Percentile68.42% | EvidenceC | Evaluated |
| BenchmarkLM Arena Agent Task Outcome Explicit | Score3.84% | Rank13 | Participants44 | Percentile72.09% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Leaderboard | Score2.11% | Rank15 | Participants44 | Percentile67.44% | EvidenceA | Evaluated |
| BenchmarkHumanity's Last Exam | Score54.70% | Rank16 | Participants109 | Percentile86.11% | EvidenceC | Evaluated |
| BenchmarkLM Arena Agent Steerability | Score1.34% | Rank17 | Participants44 | Percentile62.79% | EvidenceA | Evaluated |
| BenchmarkSWE-Bench Pro | Score62.10% | Rank18 | Participants63 | Percentile72.58% | EvidenceC | Evaluated |
| BenchmarkLM Arena Webdev | Score1,604.22 rating | Rank19 | Participants107 | Percentile83.02% | EvidenceA | Evaluated |
| BenchmarkFrontierCode 1.1 | Score24.50% | Rank20 | Participants23 | Percentile13.64% | EvidenceB | Evaluated |
| BenchmarkLiveBench math (2026-06-25) | Score89.78 score | Rank20 | Participants43 | Percentile54.76% | EvidenceB | EvaluatedN/A |
| BenchmarkTerminal-Bench 2.1 | Score82.70% | Rank21 | Participants48 | Percentile57.45% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score91.20% | Rank22 | Participants256 | Percentile91.76% | EvidenceC | Evaluated |
| BenchmarkLM Arena Agent Bash Recovery Steps | Score0.67% | Rank24 | Participants44 | Percentile46.51% | EvidenceA | Evaluated |
| BenchmarkAA HLE Text No Tools | Score41.15% | Rank25 | Participants200 | Percentile87.94% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Text | Score1,470.36 rating | Rank26 | Participants218 | Percentile88.48% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,475.99 rating | Rank26 | Participants218 | Percentile88.48% | EvidenceA | Evaluated |
| BenchmarkToolathlon | Score48.20% | Rank27 | Participants42 | Percentile36.59% | EvidenceC | Evaluated |
GLM 5.2 Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenaagent tool hallucination | Categoryoverall | Rank02 | Rating / score0.01 | VotesN/A | Observations6.7M | Result date |
| Arenaagent praise complaint | Categoryoverall | Rank08 | Rating / score0.06 | VotesN/A | Observations21.9K | Result date |
| Arenaagent task outcome explicit | Categoryoverall | Rank13 | Rating / score0.04 | VotesN/A | Observations52.1K | Result date |
| Arenatext factuality | Categorykorean | Rank13 | Rating / score1,434.05 | Votes517 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryspanish | Rank13 | Rating / score1,474.13 | Votes1,250 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryjapanese | Rank14 | Rating / score1,450.78 | Votes473 | ObservationsN/A | Result date |
| Arenaagent | Categoryoverall | Rank15 | Rating / score0.02 | VotesN/A | Observations7.2M | Result date |
| Arenatext | Categoryspanish | Rank15 | Rating / score1,477.97 | Votes1,548 | ObservationsN/A | Result date |
| Arenaagent steerability | Categoryoverall | Rank17 | Rating / score0.01 | VotesN/A | Observations189.1K | Result date |
| Arenatext | Categorycreative writing | Rank17 | Rating / score1,462.73 | Votes10,217 | ObservationsN/A | Result date |
| Arenatext style control | Categoryspanish | Rank17 | Rating / score1,478.85 | Votes1,548 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry legal and government | Rank18 | Rating / score1,486.03 | Votes4,161 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry life and physical and social science | Rank18 | Rating / score1,488.79 | Votes8,550 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry medicine and healthcare | Rank18 | Rating / score1,499.28 | Votes3,134 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry entertainment and sports and media | Rank19 | Rating / score1,449.92 | Votes12,713 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry legal and government | Rank19 | Rating / score1,489.38 | Votes3,571 | ObservationsN/A | Result date |
| Arenawebdev | Categoryoverall | Rank19 | Rating / score1,604.22 | Votes16,657 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev | Rank19 | Rating / score1,604.22 | Votes16,657 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev-react | Rank19 | Rating / score1,617.11 | Votes11,346 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry legal and government | Rank20 | Rating / score1,491.20 | Votes4,161 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry writing and literature and language | Rank21 | Rating / score1,463.14 | Votes13,740 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry life and physical and social science | Rank21 | Rating / score1,497.95 | Votes8,550 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry medicine and healthcare | Rank21 | Rating / score1,491.29 | Votes3,768 | ObservationsN/A | Result date |
| Arenatext factuality | Categorycreative writing | Rank22 | Rating / score1,453.29 | Votes9,622 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry life and physical and social science | Rank22 | Rating / score1,492.12 | Votes7,907 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry mathematical | Rank22 | Rating / score1,494.33 | Votes2,786 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry medicine and healthcare | Rank23 | Rating / score1,474.71 | Votes3,768 | ObservationsN/A | Result date |
| Arenatext | Categorykorean | Rank23 | Rating / score1,439.55 | Votes988 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry mathematical | Rank23 | Rating / score1,473.96 | Votes2,341 | ObservationsN/A | Result date |
| Arenatext style control | Categorychinese | Rank23 | Rating / score1,522.56 | Votes3,696 | ObservationsN/A | Result date |
GLM 5.2 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $1.2 input, $4.18 output per 1M
- Official provider
- Zhipu AI
- Lowest third-party
- From $0.0341 input, $7 output per 1M via OpenRouter
- Tracked offerings
- 94
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderAlibaba Token Plan | Provider model IDglm-5.2 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderSenseNova (China) | Provider model IDglm-5.2 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderUnoRouter | Provider model IDglm-5.2:free | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderZ.AI Coding Plan | Provider model IDglm-5.2 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderSCNet Token Plan | Provider model IDGLM-5.2 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderAlibaba Token Plan (China) | Provider model IDglm-5.2 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderOpenRouter | Provider model IDz-ai/glm-5.2 | Regionglobal | Input / 1M$0.0341 | Output / 1M$7 | Context1M | Updated |
| ProviderNanoGPT | Provider model IDz-ai/glm-5.2 | Regionglobal | Input / 1M$0.189 | Output / 1M$0.594 | Context1M | Updated |
| ProviderKenari | Provider model IDglm-5-2 | Regionglobal | Input / 1M$0.2857 | Output / 1M$3.43 | Context1M | Updated |
| ProviderBoundless | Provider model IDglm-5.2 | Regionglobal | Input / 1M$0.34 | Output / 1M$2.3 | Context1M | Updated |
| ProviderSCX.ai | Provider model IDGLM-5.2 | Regionglobal | Input / 1M$0.55 | Output / 1M$1.78 | Context1M | Updated |
| ProviderStandard Compute | Provider model IDz-ai/glm-5.2 | Regionglobal | Input / 1M$0.5625 | Output / 1M$1.8 | Context1M | Updated |
| ProviderAmbient | Provider model IDz-ai/glm-5.2 | Regionglobal | Input / 1M$0.60 | Output / 1M$2 | Context202.8K | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDglm-5.2 | Regionglobal | Input / 1M$0.605 | Output / 1M$2.12 | Context1M | Updated |
| ProviderInceptron | Provider model IDzai-org/GLM-5.2 | Regionglobal | Input / 1M$0.62 | Output / 1M$1.19 | Context1M | Updated |
| ProviderCoreWeave | Provider model IDzai-org/GLM-5.2 | Regionglobal | Input / 1M$0.62 | Output / 1M$2.42 | Context1M | Updated |
| Providerengy | Provider model IDglm-5.2 | Regionglobal | Input / 1M$0.68 | Output / 1M$1.5 | Context262.1K | Updated |
| ProviderDeep Infra | Provider model IDzai-org/GLM-5.2 | Regionglobal | Input / 1M$0.75 | Output / 1M$2.4 | Context1M | Updated |
| ProviderVultr | Provider model IDglm-5.2 | Regionglobal | Input / 1M$0.75 | Output / 1M$3 | Context1M | Updated |
| Providerrouting.run | Provider model IDglm-5.2 | Regionglobal | Input / 1M$0.80 | Output / 1M$2.4 | Context200K | Updated |
| ProviderRequesty | Provider model IDglm-5.2 | Regionglobal | Input / 1M$0.80 | Output / 1M$2.55 | Context1M | Updated |
| ProviderVercel AI Gateway | Provider model IDzai/glm-5.2 | Regionglobal | Input / 1M$0.80 | Output / 1M$2.55 | Context1M | Updated |
| ProviderCortecs | Provider model IDglm-5.2 | Regionglobal | Input / 1M$0.90 | Output / 1M$3.24 | Context1M | Updated |
| ProviderLilac | Provider model IDzai-org/glm-5.2 | Regionglobal | Input / 1M$0.90 | Output / 1M$3 | Context524.3K | Updated |
| ProviderGMI Cloud | Provider model IDzai-org/GLM-5.2-FP8 | Regionglobal | Input / 1M$0.979 | Output / 1M$3.08 | Context1M | Updated |
| Providerai& | Provider model IDzai-org/glm-5.2 | Regionglobal | Input / 1M$1 | Output / 1M$4 | Context1M | Updated |
| ProviderMerge Gateway | Provider model IDzai/glm-5.2 | Regionglobal | Input / 1M$1.05 | Output / 1M$3.3 | Context1M | Updated |
| ProviderAlibaba (China) | Provider model IDglm-5.2 | Regionglobal | Input / 1M$1.1 | Output / 1M$3.85 | Context1M | Updated |
| ProviderAIHubMix | Provider model IDglm-5.2 | Regionglobal | Input / 1M$1.13 | Output / 1M$3.94 | Context1M | Updated |
| ProviderVolcengine Ark | Provider model IDglm-5-2-260617 | Regionglobal | Input / 1M$1.19 | Output / 1M$4.16 | Context1M | Updated |
GLM 5.2 Runtime Performance
Provider-specific output speed and catalog latency for GLM-5.2. 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 5.2 Specifications
Technical details for the model's default version.
- Version
- GLM-5.2
- Released
- Jun 16, 2026
- Knowledge cutoff
- Unknown
- Parameters
- 753B
- Context window
- 1M
- Max output
- 1M
- Inputs
- text
- Outputs
- text
- Open weights
- Yes
- License
- MIT
GLM 5.2 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-5.2 | Released | LLMBoard75.84 | Parameters753B | Context1M | Max output1M | Open weightsYes | LicenseMIT |
Models similar to GLM 5.2
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
ZA
GLM 5.3 Flash
Zhipu AI
ZA
GLM 5.3
Zhipu AI
ZA
GLM 5.1
Zhipu AI
ZA
GLM 5
Zhipu AI
ZA
GLM 4.7
Zhipu AI
ZA
GLM 5V Turbo
Zhipu AI
What is GLM 5.2?
Key information about GLM 5.2 and its available data.
2 is Zhipu AI's foundation model for long-horizon tasks, including coding-agent workloads. It is released under the MIT license and supports thinking mode, function calling, structured output, context caching, and MCP integration.
Data as of 2026-10-22.
FAQ
Common questions about GLM 5.2.
When was GLM 5.2 released?
GLM 5.2's default version was released on Jun 16, 2026.
How much does GLM 5.2 cost?
GLM 5.2's official API price is $1.2 per million input tokens and $4.18 per million output tokens via Zhipu AI. The lowest tracked third-party offer starts at $0.0341 input and $7 output via OpenRouter.
Who created GLM 5.2?
GLM 5.2 was created by Zhipu AI.
What is the context window for GLM 5.2?
The default version has a 1M token context window.
Is GLM 5.2 open weight?
Yes. The default version is marked as open weight under MIT.
How many API providers offer GLM 5.2?
94 provider offerings are linked to the default version.