Zhipu AI model product
GLM 5.3
3 is a text-only large language model from Zhipu AI for coding, agentic work, and cybersecurity tasks.
Updated Sep 8, 2026. Default version: GLM-5.3
LLMBoard Score89.0GLM-5.3
Coverage20%17 benchmark families
Context window1MTokens
Official input price$1.4Zhipu AI API
GLM 5.3 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
GLM 5.3 Benchmark Results
Benchmark scores for GLM-5.3.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkPostTrainBench | Score39.80% | Rank01 | Participants7 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkSWE-Marathon | Score42.50% | Rank01 | Participants5 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 3.0 | Score28.30% | Rank01 | Participants3 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkCyberGym | Score84.50% | Rank02 | Participants15 | Percentile92.86% | EvidenceC | Evaluated |
| BenchmarkAutomationBench | Score48.20% | Rank03 | Participants18 | Percentile88.24% | EvidenceC | Evaluated |
| BenchmarkFrontierSWE | Score78.10% | Rank03 | Participants16 | Percentile86.67% | EvidenceC | Evaluated |
| BenchmarkGDPval-AA | Score1,769.00 points | Rank03 | Participants9 | Percentile75.00% | EvidenceC | Evaluated |
| BenchmarkNL2Repo | Score58.00% | Rank03 | Participants22 | Percentile90.48% | EvidenceC | Evaluated |
| BenchmarkExploitBench | Score54.40% | Rank04 | Participants6 | Percentile40.00% | EvidenceC | Evaluated |
| BenchmarkExploitGym | Score15.00% | Rank04 | Participants5 | Percentile25.00% | EvidenceC | Evaluated |
| BenchmarkHumanity's Last Exam | Score62.50% | Rank05 | Participants103 | Percentile96.08% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 2.1 | Score88.20% | Rank05 | Participants35 | Percentile88.24% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 4.0 | Score41.80% | Rank05 | Participants13 | Percentile66.67% | EvidenceB | Evaluated |
| BenchmarkProgram Bench | Score19.00% | Rank06 | Participants7 | Percentile16.67% | EvidenceC | Evaluated |
| BenchmarkLM Arena Agent Task Outcome Explicit | Score12.10% | Rank07 | Participants49 | Percentile87.50% | EvidenceA | Evaluated |
| BenchmarkToolathlon | Score73.00% | Rank08 | Participants41 | Percentile82.50% | EvidenceC | Evaluated |
| BenchmarkAgents' Last Exam | Score28.50% | Rank10 | Participants16 | Percentile40.00% | EvidenceC | Evaluated |
| BenchmarkDeepSWE 1.1 | Score66.90% | Rank11 | Participants31 | Percentile66.67% | EvidenceC | Evaluated |
| BenchmarkLM Arena Webdev | Score1,608.96 rating | Rank12 | Participants97 | Percentile88.54% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Tool Hallucination | Score0.78% | Rank14 | Participants49 | Percentile72.92% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Praise Complaint | Score5.75% | Rank15 | Participants49 | Percentile70.83% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,473.54 rating | Rank17 | Participants210 | Percentile92.34% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,482.04 rating | Rank17 | Participants210 | Percentile92.34% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Leaderboard | Score3.80% | Rank18 | Participants49 | Percentile64.58% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Steerability | Score0.63% | Rank20 | Participants49 | Percentile60.42% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Factuality | Score1,469.30 rating | Rank20 | Participants121 | Percentile84.17% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Bash Recovery Steps | Score-0.28% | Rank30 | Participants49 | Percentile39.58% | EvidenceA | Evaluated |
GLM 5.3 Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext | Categoryindustry mathematical | Rank04 | Rating / score1,519.18 | Votes395 | ObservationsN/A | Result date |
| Arenatext style control | Categoryhard prompts english | Rank04 | Rating / score1,523.90 | Votes2,085 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry mathematical | Rank04 | Rating / score1,521.24 | Votes395 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryhard prompts english | Rank05 | Rating / score1,517.63 | Votes2,036 | ObservationsN/A | Result date |
| Arenatext style control | Categorymath | Rank05 | Rating / score1,514.21 | Votes300 | ObservationsN/A | Result date |
| Arenatext | Categoryhard prompts english | Rank06 | Rating / score1,507.86 | Votes2,085 | ObservationsN/A | Result date |
| Arenatext | Categorymath | Rank06 | Rating / score1,507.96 | Votes300 | ObservationsN/A | Result date |
| Arenatext style control | Categoryenglish | Rank06 | Rating / score1,501.68 | Votes3,145 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry medicine and healthcare | Rank06 | Rating / score1,509.71 | Votes570 | ObservationsN/A | Result date |
| Arenaagent task outcome explicit | Categoryoverall | Rank07 | Rating / score0.12 | VotesN/A | Observations34.9K | Result date |
| Arenatext | Categoryexpert | Rank07 | Rating / score1,516.74 | Votes818 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryenglish | Rank07 | Rating / score1,490.15 | Votes3,141 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryexpert | Rank07 | Rating / score1,522.16 | Votes678 | ObservationsN/A | Result date |
| Arenatext | Categoryenglish | Rank08 | Rating / score1,492.34 | Votes3,145 | ObservationsN/A | Result date |
| Arenatext style control | Categoryexpert | Rank09 | Rating / score1,523.26 | Votes818 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry medicine and healthcare | Rank10 | Rating / score1,488.93 | Votes570 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry software and it services | Rank10 | Rating / score1,500.14 | Votes2,941 | ObservationsN/A | Result date |
| Arenatext | Categoryinstruction following | Rank10 | Rating / score1,479.29 | Votes2,728 | ObservationsN/A | Result date |
| Arenatext | Categorylonger query | Rank10 | Rating / score1,488.09 | Votes3,770 | ObservationsN/A | Result date |
| Arenatext factuality | Categorycreative writing | Rank10 | Rating / score1,465.82 | Votes1,621 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry life and physical and social science | Rank10 | Rating / score1,511.40 | Votes1,307 | ObservationsN/A | Result date |
| Arenatext | Categorycoding | Rank11 | Rating / score1,503.45 | Votes2,008 | ObservationsN/A | Result date |
| Arenatext | Categoryhard prompts | Rank11 | Rating / score1,491.47 | Votes5,079 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry entertainment and sports and media | Rank11 | Rating / score1,460.04 | Votes2,119 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry life and physical and social science | Rank11 | Rating / score1,499.90 | Votes1,307 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry entertainment and sports and media | Rank11 | Rating / score1,462.62 | Votes2,119 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry software and it services | Rank11 | Rating / score1,520.94 | Votes2,941 | ObservationsN/A | Result date |
| Arenatext | Categorycreative writing | Rank12 | Rating / score1,466.26 | Votes1,719 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry writing and literature and language | Rank12 | Rating / score1,472.91 | Votes2,204 | ObservationsN/A | Result date |
| Arenatext factuality | Categorycoding | Rank12 | Rating / score1,528.63 | Votes1,983 | ObservationsN/A | Result date |
GLM 5.3 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $1.4 input, $4.4 output per 1M
- Official provider
- Zhipu AI
- Lowest third-party
- From $0.40 input, $1.4 output per 1M via CrofAI
- Tracked offerings
- 41
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderKenari | Provider model IDglm-5-3 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderVolcengine Ark Coding Plan | Provider model IDglm-5.3 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderZhipu AI Coding Plan | Provider model IDglm-5.3 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderZ.AI Coding Plan | Provider model IDglm-5.3 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderSCNet Token Plan | Provider model IDGLM-5.3 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderCrofAI | Provider model IDglm-5.3 | Regionglobal | Input / 1M$0.40 | Output / 1M$1.4 | Context1M | Updated |
| ProviderMerge Gateway | Provider model IDzai/glm-5.3 | Regionglobal | Input / 1M$0.70 | Output / 1M$2.2 | Context1M | Updated |
| ProviderVercel AI Gateway | Provider model IDzai/glm-5.3 | Regionglobal | Input / 1M$0.70 | Output / 1M$2.2 | Context1M | Updated |
| ProviderNanoGPT | Provider model IDz-ai/glm-5.3 | Regionglobal | Input / 1M$1 | Output / 1M$3.2 | Context1M | Updated |
| Providerai& | Provider model IDzai-org/glm-5.3 | Regionglobal | Input / 1M$1 | Output / 1M$4 | Context1M | Updated |
| ProviderCortecs | Provider model IDglm-5.3 | Regionglobal | Input / 1M$1.11 | Output / 1M$3.9 | Context1M | Updated |
| ProviderVancine | Provider model IDglm-5.3 | Regionglobal | Input / 1M$1.12 | Output / 1M$3.52 | Context1M | Updated |
| ProviderAIHubMix | Provider model IDglm-5.3 | Regionglobal | Input / 1M$1.13 | Output / 1M$3.94 | Context1M | Updated |
| ProviderDeep Infra | Provider model IDzai-org/GLM-5.3 | Regionglobal | Input / 1M$1.2 | Output / 1M$4 | Context1M | Updated |
| ProviderCrossModel | Provider model IDz-ai/glm-5.3 | Regionglobal | Input / 1M$1.2 | Output / 1M$4.4 | Context1M | Updated |
| ProviderVivgrid | Provider model IDglm-5.3 | Regionglobal | Input / 1M$1.2 | Output / 1M$4.2 | Context1M | Updated |
| ProviderRequesty | Provider model IDglm-5.3 | Regionglobal | Input / 1M$1.2 | Output / 1M$4.2 | Context1M | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDglm-5.3 | Regionglobal | Input / 1M$1.2 | Output / 1M$4 | Context1M | Updated |
| ProviderOrcaRouter | Provider model IDz-ai/glm-5.3 | Regionglobal | Input / 1M$1.26 | Output / 1M$3.96 | Context1M | Updated |
| ProviderOfox | Provider model IDz-ai/glm-5.3 | Regionglobal | Input / 1M$1.26 | Output / 1M$3.96 | Context1M | Updated |
| ProviderCloudflare Workers AI | Provider model ID@cf/zai-org/glm-5.3 | Regionglobal | Input / 1M$1.4 | Output / 1M$4.4 | Context1.3M | Updated |
| ProviderTokenGo | Provider model IDz-ai/glm-5.3 | Regionglobal | Input / 1M$1.4 | Output / 1M$4.4 | Context1M | Updated |
| ProviderHugging Face | Provider model IDzai-org/GLM-5.3 | Regionglobal | Input / 1M$1.4 | Output / 1M$4.4 | Context1M | Updated |
| ProviderOpenRouter | Provider model IDz-ai/glm-5.3 | Regionglobal | Input / 1M$1.4 | Output / 1M$4.4 | Context1.3M | Updated |
| ProviderZ.AI | Provider model IDglm-5.3 | Regionglobal | Input / 1M$1.4 | Output / 1M$4.4 | Context1M | Updated |
| ProviderOpenCode Go | Provider model IDglm-5.3 | Regionglobal | Input / 1M$1.4 | Output / 1M$4.4 | Context1M | Updated |
| ProviderDigitalOcean | Provider model IDglm-5.3 | Regionglobal | Input / 1M$1.4 | Output / 1M$4.4 | Context1M | Updated |
| ProviderTogether AI | Provider model IDzai-org/GLM-5.3 | Regionglobal | Input / 1M$1.4 | Output / 1M$4.4 | Context1M | Updated |
| ProviderFriendli | Provider model IDzai-org/GLM-5.3 | Regionglobal | Input / 1M$1.4 | Output / 1M$4.4 | Context1M | Updated |
| ProviderZhipu AI | Provider model IDglm-5.3 | Regionglobal | Input / 1M$1.4 | Output / 1M$4.4 | Context1M | Updated |
GLM 5.3 Runtime Performance
Provider-specific output speed and catalog latency for GLM-5.3. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderFriendliAI | Output Speed472.69 tok/s | Catalog Latency1.50 s | Max Input1M | Max Output131.1K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
GLM 5.3 Specifications
Technical details for the model's default version.
- Version
- GLM-5.3
- Released
- Aug 14, 2026
- Knowledge cutoff
- Unknown
- Parameters
- 753B
- Context window
- 1M
- Max output
- 131.1K
- Inputs
- text
- Outputs
- text
- Open weights
- Yes
- License
- GLM-5.3 License
GLM 5.3 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-5.3 | Released | LLMBoard88.97 | Parameters753B | Context1M | Max output131.1K | Open weightsYes | LicenseGLM-5.3 License |
Models similar to GLM 5.3
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
ZA
GLM 5.3 Flash
Zhipu AI
ZA
GLM 5.2
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 5.3?
Key information about GLM 5.3 and its available data.
2. It supports a 1M-token context window, 128K maximum output, function calling, structured output, context caching, and configurable reasoning effort levels.
Data as of 2026-09-08.
FAQ
Common questions about GLM 5.3.
When was GLM 5.3 released?
GLM 5.3's default version was released on Aug 14, 2026.
How much does GLM 5.3 cost?
GLM 5.3's official API price is $1.4 per million input tokens and $4.4 per million output tokens via Zhipu AI. The lowest tracked third-party offer starts at $0.40 input and $1.4 output via CrofAI.
Who created GLM 5.3?
GLM 5.3 was created by Zhipu AI.
What is the context window for GLM 5.3?
The default version has a 1M token context window.
Is GLM 5.3 open weight?
Yes. The default version is marked as open weight under GLM-5.3 License.
How many API providers offer GLM 5.3?
41 provider offerings are linked to the default version.