llmboard.aiAI model intelligence
Home

Model Rankings

OverallOpen ModelsAgentCodingReasoningMathKnowledgeInstruction FollowingTextVision
Image GenerationImage Editing
Video GenerationImage to VideoVideo Editing
Text to SpeechSpeech to Text
Embeddings

Efficiency

Chat Token PricingImage PricingVideo PricingAudio Pricing
Chat Speed & LatencyProvider Reliability

Benchmarks

GPQAMMLU-ProAIME 2025SWE-Bench VerifiedMMLUHumanity's Last ExamLiveCodeBenchMATHHumanEvalMMMU-Pro
All Benchmarks

Tools

Model Directory

Scoring & Data

Scoring & Data
1450 models809 benchmarks

Leaderboard Center

Overall RankingCodingCore BenchmarksPrice & ValueRuntime Performance

Modalities

All ModelsImage GenerationImage EditingVideo GenerationImage-to-VideoVideo EditingText-to-SpeechSpeech-to-TextEmbeddings

Data & Methods

Scoring MethodAll Benchmarks
llmboard.aiCopyright 2026 llmboard.ai

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 Nov 18, 2026. Default version: GLM-5

LLMBoard Score64.8GLM-5
Coverage60%5 benchmark families
Context window200KTokens
Official input price$0.5976Zhipu AI API

On this page

  • Capability
  • Benchmarks
  • Arena
  • Pricing
  • Runtime
  • Specification
  • Versions
  • Similar models
  • About
  • FAQ

GLM 5 Capability Profile

This profile uses the model's current scored version. Arena ratings and prices are shown separately.

GLM-5 LLMBoard score breakdown

GLM 5 Benchmark Results

Benchmark scores for GLM-5.

15 rows
Columns

Show columns

Sort by
Benchmark
Score
Rank
Participants
Percentile
Evidence
Evaluated
Benchmarkt2-benchScore89.70%Rank03Participants23Percentile90.91%EvidenceCEvaluatedNov 17, 2026
BenchmarkSWE-Bench VerifiedScore77.80%Rank27Participants124Percentile78.86%EvidenceCEvaluatedNov 17, 2026
BenchmarkMCP AtlasScore67.80%Rank29Participants43Percentile33.33%EvidenceCEvaluatedNov 17, 2026
BenchmarkTerminal-Bench 2.0Score56.20%Rank29Participants53Percentile46.15%EvidenceCEvaluatedNov 17, 2026
BenchmarkBrowseCompScore75.90%Rank35Participants77Percentile55.26%EvidenceCEvaluatedNov 17, 2026
BenchmarkAA IFBenchScore72.31%Rank36Participants168Percentile79.04%EvidenceBEvaluatedN/A
BenchmarkLM Arena TextScore1,446.04 ratingRank47Participants221Percentile79.09%EvidenceAEvaluatedNov 11, 2026
BenchmarkLM Arena Text Style ControlScore1,457.34 ratingRank47Participants221Percentile79.09%EvidenceAEvaluatedNov 11, 2026
BenchmarkLM Arena Text FactualityScore1,451.80 ratingRank48Participants134Percentile64.66%EvidenceAEvaluatedNov 11, 2026
BenchmarkAA HLE Text No ToolsScore29.29%Rank52Participants200Percentile74.37%EvidenceBEvaluatedN/A
BenchmarkAA LCR v1.1Score75.67%Rank59Participants193Percentile69.79%EvidenceBEvaluatedN/A
BenchmarkLM Arena WebdevScore1,435.04 ratingRank65Participants111Percentile41.82%EvidenceAEvaluatedNov 15, 2026
BenchmarkAA CritPtScore2.00%Rank74Participants200Percentile63.32%EvidenceBEvaluatedN/A
BenchmarkAA Omniscience AccuracyScore26.30%Rank78Participants201Percentile61.50%EvidenceBEvaluatedN/A
BenchmarkAA GPQA DiamondScore82.02%Rank90Participants199Percentile55.05%EvidenceBEvaluatedN/A

GLM 5 Arena Results

Preference and agent-evaluation results for the default version.

30 of 85 rows
Columns

Show columns

Sort by
Arena
Category
Rank
Rating / score
Votes
Observations
Result date
Arenatext factualityCategorychineseRank18Rating / score1,525.74Votes1,390ObservationsN/AResult dateNov 11, 2026
Arenatext style controlCategorychineseRank31Rating / score1,517.27Votes2,000ObservationsN/AResult dateNov 11, 2026
ArenatextCategorychineseRank34Rating / score1,512.12Votes2,000ObservationsN/AResult dateNov 11, 2026
Arenatext factualityCategorycreative writingRank35Rating / score1,442.15Votes3,559ObservationsN/AResult dateNov 11, 2026
Arenatext style controlCategorycreative writingRank35Rating / score1,446.80Votes4,814ObservationsN/AResult dateNov 11, 2026
ArenatextCategorykoreanRank36Rating / score1,419.27Votes544ObservationsN/AResult dateNov 11, 2026
Arenatext factualityCategoryindustry entertainment and sports and mediaRank39Rating / score1,437.51Votes4,525ObservationsN/AResult dateNov 11, 2026
ArenatextCategorycreative writingRank41Rating / score1,437.14Votes4,814ObservationsN/AResult dateNov 11, 2026
ArenatextCategorymulti turnRank41Rating / score1,456.21Votes4,657ObservationsN/AResult dateNov 11, 2026
Arenatext style controlCategorykoreanRank41Rating / score1,423.63Votes544ObservationsN/AResult dateNov 11, 2026
Arenatext factualityCategoryindustry mathematicalRank42Rating / score1,458.83Votes1,125ObservationsN/AResult dateNov 11, 2026
Arenatext factualityCategoryindustry writing and literature and languageRank42Rating / score1,445.77Votes5,472ObservationsN/AResult dateNov 11, 2026
Arenatext style controlCategoryindustry entertainment and sports and mediaRank42Rating / score1,437.84Votes5,842ObservationsN/AResult dateNov 11, 2026
ArenatextCategoryenglishRank43Rating / score1,457.18Votes12,764ObservationsN/AResult dateNov 11, 2026
ArenatextCategoryindustry entertainment and sports and mediaRank43Rating / score1,425.63Votes5,842ObservationsN/AResult dateNov 11, 2026
Arenatext style controlCategorymulti turnRank43Rating / score1,471.58Votes4,657ObservationsN/AResult dateNov 11, 2026
ArenatextCategoryspanishRank44Rating / score1,454.06Votes1,121ObservationsN/AResult dateNov 11, 2026
Arenatext style controlCategoryenglishRank44Rating / score1,471.36Votes12,764ObservationsN/AResult dateNov 11, 2026
ArenatextCategoryindustry life and physical and social scienceRank45Rating / score1,460.06Votes4,675ObservationsN/AResult dateNov 11, 2026
ArenatextCategoryindustry writing and literature and languageRank45Rating / score1,436.21Votes6,950ObservationsN/AResult dateNov 11, 2026
Arenatext factualityCategorylonger queryRank45Rating / score1,468.48Votes9,411ObservationsN/AResult dateNov 11, 2026
Arenatext factualityCategorymathRank45Rating / score1,453.31Votes1,210ObservationsN/AResult dateNov 11, 2026
Arenatext style controlCategoryindustry medicine and healthcareRank45Rating / score1,478.23Votes2,112ObservationsN/AResult dateNov 11, 2026
Arenatext style controlCategoryindustry writing and literature and languageRank45Rating / score1,447.28Votes6,950ObservationsN/AResult dateNov 11, 2026
Arenatext factualityCategoryindustry life and physical and social scienceRank46Rating / score1,474.39Votes3,470ObservationsN/AResult dateNov 11, 2026
ArenatextCategoryexclude tiesRank47Rating / score1,443.18Votes20,991ObservationsN/AResult dateNov 11, 2026
ArenatextCategoryoverallRank47Rating / score1,446.04Votes28,979ObservationsN/AResult dateNov 11, 2026
Arenatext factualityCategoryenglishRank47Rating / score1,464.41Votes12,388ObservationsN/AResult dateNov 11, 2026
Arenatext factualityCategoryindustry business and management and financial operationsRank47Rating / score1,457.96Votes4,481ObservationsN/AResult dateNov 11, 2026
Arenatext factualityCategoryindustry legal and governmentRank47Rating / score1,466.55Votes1,646ObservationsN/AResult dateNov 11, 2026

GLM 5 Pricing

Official vendor API pricing appears first, followed by individual provider offers.

Official API
$0.5976 input, $2.69 output per 1M
Official provider
Zhipu AI
Lowest third-party
From $0.40 input, $1.75 output per 1M via Vultr
Tracked offerings
40
30 of 40 rows
Columns

Show columns

Sort by
Provider
Provider model ID
Region
Input / 1M
Output / 1M
Context
Updated
ProviderAlibaba Token PlanProvider model IDglm-5RegionglobalInput / 1MN/AOutput / 1MN/AContext202.8KUpdatedNov 18, 2026
ProviderAlibaba Coding Plan (China)Provider model IDglm-5RegionglobalInput / 1MN/AOutput / 1MN/AContext202.8KUpdatedNov 18, 2026
ProviderAlibaba Coding PlanProvider model IDglm-5RegionglobalInput / 1MN/AOutput / 1MN/AContext202.8KUpdatedNov 18, 2026
ProviderTencent Coding Plan (China)Provider model IDglm-5RegionglobalInput / 1MN/AOutput / 1MN/AContext202.8KUpdatedNov 18, 2026
ProviderSCNet Token PlanProvider model IDGLM-5RegionglobalInput / 1MN/AOutput / 1MN/AContext204.8KUpdatedNov 18, 2026
ProviderAlibaba Token Plan (China)Provider model IDglm-5RegionglobalInput / 1MN/AOutput / 1MN/AContext202.8KUpdatedNov 18, 2026
ProviderVultrProvider model IDglm-5.x-mentholRegionglobalInput / 1M$0.40Output / 1M$1.75Context202.8KUpdatedNov 18, 2026
ProviderAlibaba (China)Provider model IDglm-5RegionglobalInput / 1M$0.573Output / 1M$2.58Context202.8KUpdatedNov 18, 2026
ProviderDevPass (LLM Gateway)Provider model IDglm-5RegionglobalInput / 1M$0.573Output / 1M$2.58Context202.8KUpdatedNov 18, 2026
ProviderZenMuxProvider model IDz-ai/glm-5RegionglobalInput / 1M$0.58Output / 1M$2.6Context200KUpdatedNov 18, 2026
ProviderZhipu AIProvider model IDglm-5RegionglobalInput / 1M$0.5976Output / 1M$2.69Context204.8KUpdatedNov 18, 2026
ProviderNanoGPTProvider model IDz-ai/glm-5RegionglobalInput / 1M$0.60Output / 1M$1.9Context200KUpdatedNov 18, 2026
ProviderDeep InfraProvider model IDzai-org/GLM-5RegionglobalInput / 1M$0.60Output / 1M$2.08Context202.8KUpdatedNov 18, 2026
ProviderCrossModelProvider model IDz-ai/glm-5RegionglobalInput / 1M$0.60Output / 1M$3Context200KUpdatedNov 18, 2026
ProviderFastRouterProvider model IDz-ai/glm-5RegionglobalInput / 1M$0.60Output / 1M$2.08Context204.8KUpdatedNov 18, 2026
ProviderGMI CloudProvider model IDzai-org/GLM-5-FP8RegionglobalInput / 1M$0.60Output / 1M$1.92Context202.8KUpdatedNov 18, 2026
Provider302.AIProvider model IDglm-5RegionglobalInput / 1M$0.60Output / 1M$2.6Context204.8KUpdatedNov 18, 2026
ProviderDInferenceProvider model IDglm-5RegionglobalInput / 1M$0.75Output / 1M$2.4Context200KUpdatedNov 18, 2026
ProviderMeganovaProvider model IDzai-org/GLM-5RegionglobalInput / 1M$0.80Output / 1M$2.56Context202.8KUpdatedNov 18, 2026
ProviderTokenGoProvider model IDz-ai/glm-5RegionglobalInput / 1M$0.89Output / 1M$3.26Context204.8KUpdatedNov 18, 2026
ProviderOrcaRouterProvider model IDz-ai/glm-5RegionglobalInput / 1M$1Output / 1M$3.2Context204.8KUpdatedNov 18, 2026
ProviderVertexProvider model IDzai-org/glm-5-maasRegionglobalInput / 1M$1Output / 1M$3.2Context200KUpdatedNov 18, 2026
ProviderHugging FaceProvider model IDzai-org/GLM-5RegionglobalInput / 1M$1Output / 1M$3.2Context202.8KUpdatedNov 18, 2026
ProviderImpossiblProvider model IDzai/glm-5RegionglobalInput / 1M$1Output / 1M$3.2Context204.8KUpdatedNov 18, 2026
ProviderOpenRouterProvider model IDz-ai/glm-5RegionglobalInput / 1M$1Output / 1M$3.2Context204.8KUpdatedNov 18, 2026
ProviderZ.AIProvider model IDglm-5RegionglobalInput / 1M$1Output / 1M$3.2Context204.8KUpdatedNov 18, 2026
ProviderAmazon BedrockProvider model IDzai.glm-5RegionglobalInput / 1M$1Output / 1M$3.2Context202.8KUpdatedNov 18, 2026
ProviderMerge GatewayProvider model IDzai/glm-5RegionglobalInput / 1M$1Output / 1M$3.2Context200KUpdatedNov 18, 2026
ProviderTogether AIProvider model IDzai-org/GLM-5RegionglobalInput / 1M$1Output / 1M$3.2Context202.8KUpdatedNov 18, 2026
ProviderOfoxProvider model IDz-ai/glm-5RegionglobalInput / 1M$1Output / 1M$3.2Context204.8KUpdatedNov 18, 2026

GLM 5 Runtime Performance

Provider-specific output speed and catalog latency for GLM-5. Runtime does not affect the capability score.

1 row
Columns

Show columns

Sort by
Provider
Output Speed
Catalog Latency
Max Input
Max Output
Updated
ProviderZAIOutput Speed30.00 tok/sCatalog Latency3.00 sMax Input200KMax Output128KUpdatedNov 18, 2026

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.

1 row
Columns

Show columns

Sort by
Version
Released
LLMBoard
Parameters
Context
Max output
Open weights
License
VersionGLM-5ReleasedFeb 11, 2026LLMBoard64.85Parameters744BContext200KMax output128KOpen weightsNoLicenseMIT

Models similar to GLM 5

Recommendations prioritize the same model type and family, then the closest LLMBoard score.

#87+1.03
ZA

GLM 5.3 FlashX Legal

Zhipu AI

65.88 LLMBoard

Details
#86+1.09
ZA

GLM 5.1

Zhipu AI

65.94 LLMBoard

Details
#119-7.88
ZA

GLM 4.7

Zhipu AI

56.97 LLMBoard

Details
#50+9.29
ZA

GLM 5.2

Zhipu AI

74.14 LLMBoard

Details
#142-13.85
ZA

GLM 4.6

Zhipu AI

51.00 LLMBoard

Details
#32+14.10
ZA

GLM 5.3 Flash

Zhipu AI

78.95 LLMBoard

Details

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 2026-11-17.

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 $0.5976 per million input tokens and $2.69 per million output tokens via Zhipu AI. The lowest tracked third-party offer starts at $0.40 input and $1.75 output via Vultr.

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?

40 provider offerings are linked to the default version.

Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.