GLM-5.2 (max) - Intelligence, Performance & Price Analysis GLM-5.2 (max) - Intelligence, Performance & Price Analysis Artificial AnalysisModels Speech, Image, Video, Music •Open weights model •Released June 2026 GLM-5.2 (max) Intelligence, Performance & Price Analysis API Provider Benchmarks Artificial Analysis Intelligence Index 4 out of 4 units for Intelligence. Output tokens per second 4 out of 4 units for Speed. 4 out of 4 units for Price. 3 out of 4 units for Cache Hit Price. Output tokens from Intelligence Index 3 out of 4 units for Verbosity. GLM-5.2 (max) is amongst the leading models in intelligence, but particularly expensive when comparing to other open weight models of similar size. It's also notably fast, however somewhat verbose. The model supports text input, outputs text, and has a 1m tokens context window. GLM-5.2 (max) scores 51 on the Artificial Analysis Intelligence Index, placing it well above average among comparable models (averaging 24). When evaluating the Intelligence Index, it generated 140M tokens, which is somewhat verbose in comparison to the average of 110M. Pricing for GLM-5.2 (max) is $1.40 per 1M input tokens (expensive, average: $0.42) and $4.40 per 1M output tokens (expensive, average: $1.25). In total, it cost $867.88 to evaluate GLM-5.2 (max) on the Intelligence Index. At 111 tokens per second, GLM-5.2 (max) is notably fast (59). Technical specifications ReasoningYesThis page shows the reasoning version of this model. A non-reasoning variant may also exist. Context window1m~1500 A4 pages of size 12 Arial font Total parameters753B Active parameters40BNumber of parameters active per token during inference Model weightsHugging Face 92 models in this class Metrics are compared against models of the same class: Non-reasoning models → compared only with other non-reasoning models Reasoning models → compared across both reasoning and non-reasoning Open weights models → compared only with other open weights models of the same size class: Tiny: ≤4B parameters Small: 4B-40B parameters Medium: 40B-150B parameters Large: >150B parameters Proprietary models → compared across proprietary and open weights models of the same price range, using a blended 3:1 input/output price ratio: <$0.15 per 1M tokens $0.15-$1 per 1M tokens Model ComparisonAPI Provider Benchmarks Artificial Analysis Intelligence Index · Higher is better Not currently available {"@context":"https://schema.org","@type":"Dataset","name":"Intelligence","creator":{"@type":"Organization","name":"Artificial Analysis","url":"https://artificialanalysis.ai"},"description":"Artificial Analysis Intelligence Index · Higher is better · Evaluation results measured independently by Artificial Analysis","measurementTechnique":"Independent test run by Artificial Analysis on dedicated hardware.","spatialCoverage":"Worldwide","keywords":["analytics","llm","AI","benchmark","model","gpt","claude"],"license":"https://artificialanalysis.ai/docs/legal/Terms-of-Use.pdf","isAccessibleForFree":true,"citation":"Artificial Analysis (2025). LLM benchmarks dataset. https://artificialanalysis.ai","data":[{"label":"Claude Fable 5 (with fallback)","artificialAnalysisIntelligenceIndex":59.8606463217303,"detailsUrl":"/models/claude-fable-5"},{"label":"GPT-5.5 (xhigh)","artificialAnalysisIntelligenceIndex":54.8375984166433,"detailsUrl":"/models/gpt-5-5"},{"label":"GLM-5.2 (max)","artificialAnalysisIntelligenceIndex":50.6663591160109,"detailsUrl":"/models/glm-5-2"},{"label":"Gemini 3.1 Pro Preview","artificialAnalysisIntelligenceIndex":46.4594206066426,"detailsUrl":"/models/gemini-3-1-pro-preview"},{"label":"MiniMax-M3","artificialAnalysisIntelligenceIndex":44.4372686326056,"detailsUrl":"/models/minimax-m3"},{"label":"DeepSeek V4 Pro (Max)","artificialAnalysisIntelligenceIndex":44.2735554261611,"detailsUrl":"/models/deepseek-v4-pro"},{"label":"Muse Spark","artificialAnalysisIntelligenceIndex":43.0555563074727,"detailsUrl":"/models/muse-spark"},{"label":"Kimi K2.6","artificialAnalysisIntelligenceIndex":42.8413910763059,"detailsUrl":"/models/kimi-k2-6"},{"label":"Nemotron 3 Ultra","artificialAnalysisIntelligenceIndex":37.7619546243905,"detailsUrl":"/models/nvidia-nemotron-3-ultra-550b-a55b"},{"label":"Grok 4.3 (high)","artificialAnalysisIntelligenceIndex":37.5766393431307,"detailsUrl":"/models/grok-4-3"},{"label":"gpt-oss-120b (high)","artificialAnalysisIntelligenceIndex":23.8309678073278,"detailsUrl":"/models/gpt-oss-120b"}]} Output tokens per second · Higher is better {"@context":"https://schema.org","@type":"Dataset","name":"Speed","creator":{"@type":"Organization","name":"Artificial Analysis","url":"https://artificialanalysis.ai"},"description":"Output tokens per second · Higher is better · Evaluation results measured independently by Artificial Analysis","measurementTechnique":"Independent test run by Artificial Analysis on dedicated hardware.","spatialCoverage":"Worldwide","keywords":["analytics","llm","AI","benchmark","model","gpt","claude"],"license":"https://artificialanalysis.ai/docs/legal/Terms-of-Use.pdf","isAccessibleForFree":true,"citation":"Artificial Analysis (2025). LLM benchmarks dataset. https://artificialanalysis.ai","data":[{"label":"gpt-oss-120b (high)","medianOutputSpeed":342.175228559504,"detailsUrl":"/models/gpt-oss-120b"},{"label":"Grok 4.3 (high)","medianOutputSpeed":171.460154677232,"detailsUrl":"/models/grok-4-3"},{"label":"Nemotron 3 Ultra","medianOutputSpeed":166.047131698526,"detailsUrl":"/models/nvidia-nemotron-3-ultra-550b-a55b"},{"label":"Gemini 3.1 Pro Preview","medianOutputSpeed":122.105728018443,"detailsUrl":"/models/gemini-3-1-pro-preview"},{"label":"GLM-5.2 (max)","medianOutputSpeed":110.723263714432,"detailsUrl":"/models/glm-5-2"},{"label":"MiniMax-M3","medianOutputSpeed":61.1845145050286,"detailsUrl":"/models/minimax-m3"},{"label":"GPT-5.5 (xhigh)","medianOutputSpeed":59.9988146730205,"detailsUrl":"/models/gpt-5-5"},{"label":"DeepSeek V4 Pro (Max)","medianOutputSpeed":58.4206088703861,"detailsUrl":"/models/deepseek-v4-pro"},{"label":"Kimi K2.6","medianOutputSpeed":45.6809609707683,"detailsUrl":"/models/kimi-k2-6"}]} Weighted average cost (USD) per Intelligence Index task · Lower is better Not currently available {"@context":"https://schema.org","@type":"Dataset","name":"Cost per Task","creator":{"@type":"Organization","name":"Artificial Analysis","url":"https://artificialanalysis.ai"},"description":"Weighted average cost (USD) per Intelligence Index task · Lower is better · Evaluation results measured independently by Artificial Analysis","measurementTechnique":"Independent test run by Artificial Analysis on dedicated hardware.","spatialCoverage":"Worldwide","keywords":["analytics","llm","AI","benchmark","model","gpt","claude"],"license":"https://artificialanalysis.ai/docs/legal/Terms-of-Use.pdf","isAccessibleForFree":true,"citation":"Artificial Analysis (2025). LLM benchmarks dataset. https://artificialanalysis.ai","data":[{"label":"DeepSeek V4 Pro (Max)","costPerIntelligenceIndexTask":0.04843120557386489,"detailsUrl":"/models/deepseek-v4-pro"},{"label":"gpt-oss-120b (high)","costPerIntelligenceIndexTask":0.06067164425252873,"detailsUrl":"/models/gpt-oss-120b"},{"label":"MiniMax-M3","costPerIntelligenceIndexTask":0.15667113197545668,"detailsUrl":"/models/minimax-m3"},{"label":"Grok 4.3 (high)","costPerIntelligenceIndexTask":0.185819299545001,"detailsUrl":"/models/grok-4-3"},{"label":"Nemotron 3 Ultra","costPerIntelligenceIndexTask":0.24459721669474674,"detailsUrl":"/models/nvidia-nemotron-3-ultra-550b-a55b"},{"label":"Kimi K2.6","costPerIntelligenceIndexTask":0.31455659115785106,"detailsUrl":"/models/kimi-k2-6"},{"label":"Gemini 3.1 Pro Preview","costPerIntelligenceIndexTask":0.33720385533357705,"detailsUrl":"/models/gemini-3-1-pro-preview"},{"label":"GLM-5.2 (max)","costPerIntelligenceIndexTask":0.41389562003906394,"detailsUrl":"/models/glm-5-2"},{"label":"GPT-5.5 (xhigh)","costPerIntelligenceIndexTask":1.0688263760595473,"detailsUrl":"/models/gpt-5-5"},{"label":"Claude Fable 5 (with fallback)","costPerIntelligenceIndexTask":3.2542013482460366,"detailsUrl":"/models/claude-fable-5"}]} IntelligenceUpdatedOpennessIntelligence Index ComparisonsToken UseUpdatedPrice and CostUpdatedContext WindowSpeedUpdatedLatencyEnd-to-End Response TimeModel Size (Open Weights Models Only) Artificial Analysis Intelligence IndexUpdatedCoding IndexAgentic Index Artificial Analysis Intelligence Index Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR Add model from specific provider Not currently available Reasoning models are indicated by a lightbulb icon {"@context":"https://schema.org","@type":"Dataset","name":"Artificial Analysis Intelligence Index","creator":{"@type":"Organization","name":"Artificial Analysis","url":"https://artificialanalysis.ai"},"description":"Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR · Evaluation results measured independently by Artificial Analysis","measurementTechnique":"Independent test run by Artificial Analysis on dedicated hardware.","spatialCoverage":"Worldwide","keywords":["analytics","llm","AI","benchmark","model","gpt","claude"],"license":"https://artificialanalysis.ai/docs/legal/Terms-of-Use.pdf","isAccessibleForFree":true,"citation":"Artificial Analysis (2025). LLM benchmarks dataset. https://artificialanalysis.ai","data":[{"label":"Claude Fable 5 (with fallback)","intelligenceIndex":59.8606463217303,"detailsUrl":"/models/claude-fable-5"},{"label":"GPT-5.5 (xhigh)","intelligenceIndex":54.8375984166433,"detailsUrl":"/models/gpt-5-5"},{"label":"GLM-5.2 (max)","intelligenceIndex":50.6663591160109,"detailsUrl":"/models/glm-5-2"},{"label":"Gemini 3.1 Pro Preview","intelligenceIndex":46.4594206066426,"detailsUrl":"/models/gemini-3-1-pro-preview"},{"label":"MiniMax-M3","intelligenceIndex":44.4372686326056,"detailsUrl":"/models/minimax-m3"},{"label":"DeepSeek V4 Pro (Max)","intelligenceIndex":44.2735554261611,"detailsUrl":"/models/deepseek-v4-pro"},{"label":"Muse Spark","intelligenceIndex":43.0555563074727,"detailsUrl":"/models/muse-spark"},{"label":"Kimi K2.6","intelligenceIndex":42.8413910763059,"detailsUrl":"/models/kimi-k2-6"},{"label":"MiMo-V2.5-Pro","intelligenceIndex":42.2394366693508,"detailsUrl":"/models/mimo-v2-5-pro"},{"label":"Kimi K2.7 Code","intelligenceIndex":41.9493685067994,"detailsUrl":"/models/kimi-k2-7-code"},{"label":"DeepSeek V4 Flash (Max)","intelligenceIndex":40.2825017625236,"detailsUrl":"/models/deepseek-v4-flash"},{"label":"GLM-5.1","intelligenceIndex":40.1570857627689,"detailsUrl":"/models/glm-5-1"},{"label":"MiniMax-M2.7","intelligenceIndex":38.1344947250387,"detailsUrl":"/models/minimax-m2-7"},{"label":"Nemotron 3 Ultra","intelligenceIndex":37.7619546243905,"detailsUrl":"/models/nvidia-nemotron-3-ultra-550b-a55b"},{"label":"Grok 4.3 (high)","intelligenceIndex":37.5766393431307,"detailsUrl":"/models/grok-4-3"},{"label":"Qwen3.5 397B A17B","intelligenceIndex":33.6817059499116,"detailsUrl":"/models/qwen3-5-397b-a17b"},{"label":"Ring-2.6-1T","intelligenceIndex":30.5727263188268,"detailsUrl":"/models/ring-2-6-1t"},{"label":"Step 3.7 Flash","intelligenceIndex":29.7283976225226,"detailsUrl":"/models/step-3-7-flash"},{"label":"gpt-oss-120b (high)","intelligenceIndex":23.8309678073278,"detailsUrl":"/models/gpt-oss-120b"},{"label":"Llama 4 Maverick","intelligenceIndex":14.2657978659374,"detailsUrl":"/models/llama-4-maverick"}]} Artificial Analysis Intelligence Index Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them. Open Weights / ProprietaryReasoning / Non-Reasoning Artificial Analysis Intelligence Index by Open Weights / Proprietary Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR Links
Browse another page: |