Skip to content
AI Atlas
ModelDeprecatedOpen weightsIdentity probable

GLM 5

Z.ai (Zhipu AI)family · GLM5huggingface.co/zai-org/GLM-5

GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading...

Open in Graph
data quality72

Updated 26 min ago · first seen 11 Sept 2026

model_01M294WW58QZ2KAA2XSGNFKSQ5

Overview

Identity

Canonical model
Yesidentity confidence: mediumOne row per real model release. Artifacts (checkpoints, quantisations, conversions) and folded evaluation variants point here.
Official checkpoints
official_checkpoints = hf_repo identifiers carried by the model itself; artifacts are separate entities pointing here through canonical_id.
Artifacts
1 quantization0 official · 1 third-partySeparate entities (checkpoint · quantization · conversion · packaging) pointing to this model through canonical_id.
Provider deployments
2
API aliases
glm-5glm-5-non-reasoningz-ai/glm-5Identifiers under which providers and evaluators refer to this model.
Folded evaluation variants
1Effort / thinking variants (…-high, …-non-reasoning) are result configurations of this model, not separate models. Their old URLs redirect here.

Openness

Open weights— weights downloadable under MIT; commercial use allowed; redistribution allowed; derivatives allowed; 4 dimensions unknown.

Weights downloadable under a permissive or Creative Commons licence allowing commercial use; code or data may be missing.

  • Weights

    Yes

  • Inference code

    —

  • Training code

    —

  • Training data

    —

  • Dataset

    —

  • Commercial use

    Yes

  • Redistribution

    Yes

  • Derivatives

    Yes

Licence: MIT License (permissive · SPDX MIT · stated as “mit”)

dimensions marked null are unknown, not false

Key facts

Release date

Source:OpenRouter public model & pricing listingT2observed 16 h agomedium

Status

Source:Artificial AnalysisT2observed 15 h agomedium

Model card
huggingface.co/zai-org/GLM-5

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 16 h agomedium

Openrouter id

Source:OpenRouter public model & pricing listingT2observed 16 h agomedium

Architecture

Architecture

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 15 h agomedium

Model type

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 15 h agomedium

Parameters

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 16 h agomedium

Weights dtype

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 15 h agomedium

File size

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 15 h agomedium

Library name

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 15 h agomedium

Pipeline tag

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 16 h agomedium

Hugging Face repo

Source:OpenRouter public model & pricing listingT2observed 16 h agomedium

Capabilities

Modalities

Modalities
text
Input
text
Output
text

Capabilities

  • Tool calling

    Yes

    OpenRouter public model & pricing listing · T2

  • Structured output

    Yes

    OpenRouter public model & pricing listing · T2

  • Reasoning

    Yes

    Artificial Analysis · T2

  • Vision

    Unavailable

  • Audio

    Unavailable

  • Fine-tuning available

    Unavailable

Context window

Source:OpenRouter public model & pricing listingT2observed 14 h agomedium

Max output

Source:OpenRouter public model & pricing listingT2observed 16 h agomedium

Languages

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 15 h agomedium

Benchmarks26

Compare with another model →

Comparable same task and conditions · Partially comparable same task, conditions differ (effort, temperature, judge) · Not comparable different variant or metric

Benchmark results grouped by comparability group
Benchmark · groupBest scoreTrustConfigurationResultsvs leaderEvaluatedSource
Terminal-Benchagentic · accuracy · variant=hard · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisvarianthardreasoningonconditions differ across rows → partially comparable4−22.7 ptvs gpt-5.6-solobs. 12 Sept 2026artificialanalysis.aiT2
τ²-benchagentic · pass^1 · variant=Telecom · evaluator=Artificial AnalysisIndependentevaluatorArtificial AnalysisvariantTelecomreasoningonconditions differ across rows → partially comparable2non-primary groupobs. 12 Sept 2026artificialanalysis.aiT2
τ²-benchagentic · pass^1 · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysis2−0.87 ptvs Z.ai GLM 5.2obs. 11 Sept 2026artificialanalysis.aiT2
SWE-bench Multilingualcoding · resolved · board=Multilingual · system=mini-SWE-agentOfficial boardboardMultilingualsystemmini-SWE-agent1−3.00 ptvs gemini-3-flash13 Feb 2026swebench.comT2
SWE-bench Verifiedcoding · resolved · board=Verified · system=mini-SWE-agentOfficial boardboardVerifiedsystemmini-SWE-agentreasoning_efforthighconditions differ across rows → partially comparable1−4.00 ptvs Claude Opus 4.517 Feb 2026swebench.comT2
Artificial Analysis Intelligence Indexcomposite · indexIndependentreasoningonversion4.3conditions differ across rows → partially comparable4−25.5vs Claude Fable 5.1obs. 12 Sept 2026artificialanalysis.aiT2
IFBenchinstruction-following · accuracy · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisreasoningonconditions differ across rows → partially comparable4−11.0 ptvs Grok 4.3obs. 12 Sept 2026artificialanalysis.aiT2
Humanity's Last Examknowledge · accuracy · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisreasoningonconditions differ across rows → partially comparable4−29.8 ptvs Claude Fable 5.1obs. 12 Sept 2026artificialanalysis.aiT2
GPQA Diamondreasoning · accuracy · variant=Diamond · evaluator=Artificial AnalysisIndependentevaluatorArtificial AnalysisvariantDiamondreasoningonconditions differ across rows → partially comparable2non-primary groupobs. 12 Sept 2026artificialanalysis.aiT2
GPQA Diamondreasoning · accuracy · variant=GPQA Diamond · evaluator=Artificial AnalysisIndependentevaluatorArtificial AnalysisvariantGPQA Diamond2−14.2 ptvs gpt-6-astraobs. 11 Sept 2026artificialanalysis.aiT2

Current rows only, grouped by benchmark → canonical metric → comparability group (task configuration). Effort variants folded into this model appear as rows of the same group. 26 current rows in total. “vs leader” compares with the current leader of the benchmark's primary group only; other groups are not directly comparable. Comparability rules →

Providers & Pricing2

All offers in the price terminal →
Provider deployments, cheapest output first
ProviderContextInput / 1MCached inOutput / 1MStatusObservedSource
OpenRoutercheapest outputz-ai/glm-5198Kout 128K$0.12active2 min agosince 12 Sept 2026openrouter.aiT2
Z.ai APIz-ai/glm-5198Kout 128K$0.12active7 h agosince 11 Sept 2026openrouter.aiT2

USD per 1M tokens as published by each provider; native units (per-request fees, flex/priority tiers) are kept verbatim. Rows are append-only — every price change is kept in the history below. Cost of a workload →

Price history

Step lines per provider; amber markers are recorded changes. Click a marker or a row for the evidence behind that price.

Output price · USD / 1M tokens 2 providers

Output price history of GLM 5$0$0.50$1$1.5$2$2.5Sept 26Sept 26Sept 26Sept 26Sept 26Sept 26Z.ai API: first observed → $1.92 · 11 Sept 2026OpenRouter: first observed → $1.92 · 12 Sept 2026
  • Z.ai API
  • OpenRouter
  • OpenRouterfirst observed $1.9212 Sept 2026
  • Z.ai APIfirst observed $1.9211 Sept 2026

Input price · USD / 1M tokens 2 providers

Input price history of GLM 5$0$0.20$0.40$0.60$0.80Sept 26Sept 26Sept 26Sept 26Sept 26Sept 26Z.ai API: first observed → $0.60 · 11 Sept 2026OpenRouter: first observed → $0.60 · 12 Sept 2026
  • Z.ai API
  • OpenRouter
  • OpenRouterfirst observed $0.6012 Sept 2026
  • Z.ai APIfirst observed $0.6011 Sept 2026

Hardware fit37

Estimated

3 of 37 device × quantization combinations fit.

Run locally: your machine →
Estimated hardware fit
HardwareQuantizationDevice memoryEst. memoryFits
Apple M3 Ultra4bit—434.0 GB est.Yes
Mac Studio (Apple M5 Ultra)4bit—434.0 GB est.Yes
NVIDIA DGX B2004bit1,440 GB434.0 GB est.Yes
Apple M2 Ultra4bit—434.0 GB est.No
Apple M1 Ultra4bit—434.0 GB est.No
Apple M3 Max4bit—434.0 GB est.No
Apple M4 Max4bit—434.0 GB est.No
Mac Studio (Apple M5 Max)4bit—434.0 GB est.No
MacBook Pro (Apple M5 Max)4bit—434.0 GB est.No
Apple M2 Max4bit—434.0 GB est.No
Apple M1 Max4bit—434.0 GB est.No
Apple M4 Pro4bit—434.0 GB est.No
Mac mini (Apple M5 Pro)4bit—434.0 GB est.No
MacBook Pro (Apple M5 Pro)4bit—434.0 GB est.No
Apple M3 Pro4bit—434.0 GB est.No
Apple M1 Pro4bit—434.0 GB est.No
Apple M2 Pro4bit—434.0 GB est.No
Apple M44bit—434.0 GB est.No
iMac (Apple M4)4bit—434.0 GB est.No
Mac mini (Apple M6)4bit—434.0 GB est.No
MacBook Air (Apple M5)4bit—434.0 GB est.No
MacBook Pro (Apple M5)4bit—434.0 GB est.No
Apple M24bit—434.0 GB est.No
Apple M34bit—434.0 GB est.No
Apple M14bit—434.0 GB est.No
NVIDIA GeForce RTX 30904bit24 GB434.0 GB est.No
NVIDIA GeForce RTX 40904bit24 GB434.0 GB est.No
NVIDIA GeForce RTX 50904bit32 GB434.0 GB est.No
NVIDIA A100 80GB4bit80 GB434.0 GB est.No
NVIDIA H100 SXM4bit80 GB434.0 GB est.No
NVIDIA H100 NVL4bit94 GB434.0 GB est.No
NVIDIA DGX Spark4bit128 GB434.0 GB est.No
NVIDIA H2004bit141 GB434.0 GB est.No
NVIDIA H200 NVL4bit141 GB434.0 GB est.No
NVIDIA B2004bit180 GB434.0 GB est.No
AMD Instinct MI300X4bit192 GB434.0 GB est.No
AMD Instinct MI325X4bit256 GB434.0 GB est.No
Assumptions (7)
  • Estimated, not measured: weights = parameters × bytes/param × 1.15 runtime overhead (or the observed artifact file size when one is recorded).
  • bytes/param: 4bit = 0.5, 8bit = 1.0, fp16 = 2.0 (uniform quantization, no per-layer exceptions).
  • KV cache: 2 × layers × kv_heads × head_dim × 2 bytes × context × batch when the architecture is known; otherwise 0.5 GB per 8 192 tokens (× batch), independent of architecture (GQA/MLA models need less).
  • A model 'fits' when the estimate is at most the device memory minus 2 GB reserved for the OS and framework.
  • Mixture-of-experts models are estimated on total parameters (all experts must be resident); active parameters are ignored.
  • Device memory uses the largest configuration when several are listed (e.g. Apple silicon tiers).
  • Multi-GPU: device memories are summed; interconnect bandwidth, tensor-parallel replication and pipeline bubbles are not modelled.

Lineage

Open in Graph →
Explicit derived_from / fine_tuned_from / distilled_from relations stated by sources; artifacts collapsed by kind.
DESCENDANTS 0 · ARTIFACTS1 quantizationartifacts · collapsed1 quantization — artifacts · collapsedGLM 5753.9B params · this modelGLM 5 — 753.9B params · this model

    Versions & Artifacts1

    Version history

    Context window2 changes

    11 Sept 2026→11 Sept 2026→12 Sept 2026current

    Licensefirst observation only

    11 Sept 2026current

    Max outputfirst observation only

    11 Sept 2026current

    Opennessfirst observation only

    11 Sept 2026current

    Parametersfirst observation only

    11 Sept 2026current

    Statusfirst observation only

    11 Sept 2026current

    Each hop is a claim: click a value for its source, tier and observation time. Nothing is overwritten — a new observation closes the previous claim.

    Artifacts 1

    quantization 1

    Papers1

    Timeline15

    Full timeline →
    • Listed by providerModelGLM 5Z.ai (Zhipu AI)

      OpenRouter lists GLM 5 at $0.6 in / $1.92 out per 1M tokens

      openrouter
      openrouter.ai
    • Benchmark resultModelGLM 5Z.ai (Zhipu AI)

      GLM 5 scores 43.18% on Terminal-Bench

      artificial_analysis
      artificialanalysis.ai
    • Benchmark resultModelGLM 5Z.ai (Zhipu AI)

      GLM 5 scores 98.25% on τ²-bench

      artificial_analysis
      artificialanalysis.ai
    • Benchmark resultModelGLM 5Z.ai (Zhipu AI)

      GLM 5 scores 72.31% on IFBench

      artificial_analysis
      artificialanalysis.ai
    • Benchmark resultModelGLM 5Z.ai (Zhipu AI)

      GLM 5 scores 29.29% on Humanity's Last Exam

      artificial_analysis
      artificialanalysis.ai
    • Benchmark resultModelGLM 5Z.ai (Zhipu AI)

      GLM 5 scores 82.02% on GPQA Diamond

      artificial_analysis
      artificialanalysis.ai
    • Benchmark resultModelGLM 5Z.ai (Zhipu AI)

      GLM 5 scores 27.91 on Artificial Analysis Intelligence Index

      artificial_analysis
      artificialanalysis.ai
    • Benchmark resultModelGLM 5Z.ai (Zhipu AI)

      GLM 5 scores 39.39% on Terminal-Bench

      artificial_analysis
      artificialanalysis.ai
    • Benchmark resultModelGLM 5Z.ai (Zhipu AI)

      GLM 5 scores 97.37% on τ²-bench

      artificial_analysis
      artificialanalysis.ai
    • Benchmark resultModelGLM 5Z.ai (Zhipu AI)

      GLM 5 scores 55.17% on IFBench

      artificial_analysis
      artificialanalysis.ai
    • Benchmark resultModelGLM 5Z.ai (Zhipu AI)

      GLM 5 scores 7.65% on Humanity's Last Exam

      artificial_analysis
      artificialanalysis.ai
    • Benchmark resultModelGLM 5Z.ai (Zhipu AI)

      GLM 5 scores 66.57% on GPQA Diamond

      artificial_analysis
      artificialanalysis.ai
    • Benchmark resultModelGLM 5Z.ai (Zhipu AI)

      GLM 5 scores 21.78 on Artificial Analysis Intelligence Index

      artificial_analysis
      artificialanalysis.ai
    • Property changedModelGLM 5Z.ai (Zhipu AI)

      GLM 5: reasoning changed from false to true

      ReasoningNo→Yesartificial_analysis
      artificialanalysis.ai
    • Context window changedModelGLM 5Z.ai (Zhipu AI)

      GLM 5: context length changed from 200000 to 204800

      Context window200K tokens→204.8K tokensopenrouter
      openrouter.ai

    Change history

    Temporal, append-only claims: a new observation closes the previous claim instead of overwriting it. Rewind the record with the as-of picker.
    1 claims · 1 propertiesShow all properties

    License keylicense_key1

    Claim history for License key
    ValueValid from → toStatusSourceConfidenceExtractor
    MIT → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

    Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

    Provenance

    Attributed facts

    45

    Source tiers

    T245

    Freshest observation

    26 min ago

    Conflicts

    None

    Source documents 6

    Source documents
    SourceDocumentTypeTierLast observedSnapshots
    OpenRouter public model & pricing listingopenrouter.ai/api/v1/models catalogueT2· Quality secondary2 min ago13
    Artificial Analysisartificialanalysis.ai/leaderboards/models leaderboardT2· Quality secondary26 min ago3
    Hugging Face Hub (public pages, model cards, papers)huggingface.co/zai-org/GLM-5 model_pageT2· Quality secondary2 h ago6
    Hugging Face Hub (public pages, model cards, papers)huggingface.co/models?author=zai-org&p=0&sort=downloads listingT2· Quality secondary2 h ago8
    SWE-bench leaderboardsswebench.com/ leaderboardT2· Quality secondary6 h ago1
    Hugging Face Hub (public pages, model cards, papers)huggingface.co/zai-org/GLM-5/raw/main/README.md model_cardT2· Quality secondary10 h ago1

    Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.

    Data quality (72/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →