Zhipu AI model product
GLM 5.3 Flash
3-Flash is a natively multimodal 320B-total/18B-active MoE model from Zhipu AI with a 1M-token context window.
Updated Oct 23, 2026. Default version: GLM-5.3-Flash
LLMBoard Score81.3GLM-5.3-Flash
Coverage80%15 benchmark families
Context window1MTokens
Official input price$0.1195Zhipu AI API
GLM 5.3 Flash Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
GLM 5.3 Flash Benchmark Results
Benchmark scores for GLM-5.3-Flash.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkMMVU | Score80.50% | Rank01 | Participants7 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkMVBench | Score77.80% | Rank01 | Participants18 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkToolathlon | Score78.40% | Rank01 | Participants42 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkArtificial Analysis | Score57.00% | Rank02 | Participants13 | Percentile91.67% | EvidenceC | Evaluated |
| BenchmarkGDPval-AA | Score1,773.00 points | Rank02 | Participants17 | Percentile93.75% | EvidenceC | Evaluated |
| BenchmarkChartography | Score78.00% | Rank06 | Participants6 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkLM Arena Agent Tool Hallucination | Score0.65% | Rank07 | Participants44 | Percentile86.05% | EvidenceA | Evaluated |
| BenchmarkAutomationBench | Score48.80% | Rank08 | Participants27 | Percentile73.08% | EvidenceC | Evaluated |
| BenchmarkNL2Repo | Score56.30% | Rank08 | Participants25 | Percentile70.83% | EvidenceC | Evaluated |
| BenchmarkOfficeQA Pro | Score62.40% | Rank08 | Participants12 | Percentile36.36% | EvidenceC | Evaluated |
| BenchmarkCharXiv-R | Score89.40% | Rank09 | Participants60 | Percentile86.44% | EvidenceC | Evaluated |
| BenchmarkBabyVision | Score53.40% | Rank12 | Participants16 | Percentile26.67% | EvidenceC | Evaluated |
| BenchmarkHumanity's Last Exam | Score55.30% | Rank14 | Participants109 | Percentile87.96% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 2.1 | Score84.30% | Rank16 | Participants48 | Percentile68.09% | EvidenceC | Evaluated |
| BenchmarkLM Arena Agent Task Outcome Explicit | Score2.96% | Rank16 | Participants44 | Percentile65.12% | EvidenceA | Evaluated |
| BenchmarkLM Arena Webdev | Score1,606.83 rating | Rank18 | Participants107 | Percentile83.96% | EvidenceA | Evaluated |
| BenchmarkLM Arena Vision | Score1,293.87 rating | Rank20 | Participants113 | Percentile83.04% | EvidenceA | Evaluated |
| BenchmarkAgents' Last Exam | Score26.30% | Rank21 | Participants24 | Percentile13.04% | EvidenceC | Evaluated |
| BenchmarkAA CritPt | Score15.43% | Rank23 | Participants200 | Percentile88.94% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Text | Score1,471.36 rating | Rank24 | Participants218 | Percentile89.40% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Leaderboard | Score-1.57% | Rank25 | Participants44 | Percentile44.19% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Praise Complaint | Score-2.42% | Rank25 | Participants44 | Percentile44.19% | EvidenceA | Evaluated |
| BenchmarkAA LCR v1.1 | Score80.00% | Rank25 | Participants193 | Percentile87.50% | EvidenceB | EvaluatedN/A |
| BenchmarkAA SciCode Subtasks | Score51.62% | Rank26 | Participants89 | Percentile71.59% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Vision Style Control | Score1,271.15 rating | Rank27 | Participants113 | Percentile76.79% | EvidenceA | Evaluated |
| BenchmarkAA GPQA Diamond | Score91.21% | Rank27 | Participants199 | Percentile86.87% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Agent Steerability | Score-3.37% | Rank29 | Participants44 | Percentile34.88% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,474.87 rating | Rank29 | Participants218 | Percentile87.10% | EvidenceA | Evaluated |
| BenchmarkAA HLE Text No Tools | Score39.85% | Rank30 | Participants200 | Percentile85.43% | EvidenceB | EvaluatedN/A |
| BenchmarkDeepSWE 1.1 | Score63.40% | Rank31 | Participants51 | Percentile40.00% | EvidenceC | Evaluated |
GLM 5.3 Flash 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 | Rank07 | Rating / score0.01 | VotesN/A | Observations10.6M | Result date |
| Arenatext factuality | Categorymath | Rank10 | Rating / score1,492.63 | Votes1,450 | ObservationsN/A | Result date |
| Arenatext | Categorymath | Rank11 | Rating / score1,502.73 | Votes1,820 | ObservationsN/A | Result date |
| Arenatext style control | Categorymath | Rank11 | Rating / score1,504.27 | Votes1,820 | ObservationsN/A | Result date |
| Arenavision | Categorychinese | Rank12 | Rating / score1,362.79 | Votes699 | ObservationsN/A | Result date |
| Arenatext | Categorycoding | Rank13 | Rating / score1,506.78 | Votes9,192 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry software and it services | Rank13 | Rating / score1,500.02 | Votes13,518 | ObservationsN/A | Result date |
| Arenavision style control | Categorychinese | Rank14 | Rating / score1,337.75 | Votes699 | ObservationsN/A | Result date |
| Arenatext | Categorychinese | Rank15 | Rating / score1,531.14 | Votes2,838 | ObservationsN/A | Result date |
| Arenatext | Categoryhard prompts | Rank15 | Rating / score1,490.22 | Votes22,985 | ObservationsN/A | Result date |
| Arenatext factuality | Categorykorean | Rank15 | Rating / score1,428.29 | Votes240 | ObservationsN/A | Result date |
| Arenavision | Categorydiagram | Rank15 | Rating / score1,316.97 | Votes3,995 | ObservationsN/A | Result date |
| Arenavision | Categoryenglish | Rank15 | Rating / score1,295.42 | Votes5,043 | ObservationsN/A | Result date |
| Arenaagent task outcome explicit | Categoryoverall | Rank16 | Rating / score0.03 | VotesN/A | Observations54.2K | Result date |
| Arenatext | Categoryexpert | Rank16 | Rating / score1,510.71 | Votes3,726 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry mathematical | Rank16 | Rating / score1,496.70 | Votes2,086 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryexpert | Rank16 | Rating / score1,515.66 | Votes3,306 | ObservationsN/A | Result date |
| Arenatext style control | Categorychinese | Rank16 | Rating / score1,531.98 | Votes2,838 | ObservationsN/A | Result date |
| Arenavision | Categoryhomework | Rank16 | Rating / score1,317.76 | Votes2,229 | ObservationsN/A | Result date |
| Arenawebdev | Categoryimage to webdev | Rank16 | Rating / score1,578.32 | Votes5,623 | ObservationsN/A | Result date |
| Arenatext | Categoryspanish | Rank17 | Rating / score1,474.68 | Votes1,360 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev-react | Rank17 | Rating / score1,624.31 | Votes11,613 | ObservationsN/A | Result date |
| Arenatext | Categoryhard prompts english | Rank18 | Rating / score1,488.47 | Votes8,456 | ObservationsN/A | Result date |
| Arenatext factuality | Categorychinese | Rank18 | Rating / score1,526.20 | Votes2,338 | ObservationsN/A | Result date |
| Arenawebdev | Categoryoverall | Rank18 | Rating / score1,606.83 | Votes18,264 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev | Rank18 | Rating / score1,606.83 | Votes18,264 | ObservationsN/A | Result date |
| Arenatext | Categoryinstruction following | Rank19 | Rating / score1,477.54 | Votes12,492 | ObservationsN/A | Result date |
| Arenatext style control | Categoryfrench | Rank19 | Rating / score1,501.14 | Votes1,348 | ObservationsN/A | Result date |
| Arenatext factuality | Categorycoding | Rank20 | Rating / score1,527.48 | Votes9,082 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryfrench | Rank20 | Rating / score1,496.87 | Votes911 | ObservationsN/A | Result date |
GLM 5.3 Flash Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $0.1195 input, $0.4183 output per 1M
- Official provider
- Zhipu AI
- Lowest third-party
- From $0.0052 input, $0.1985 output per 1M via OpenRouter
- Tracked offerings
- 80
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderZhipu AI Coding Plan | Provider model IDglm-5.3-flash | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderZ.AI Coding Plan | Provider model IDglm-5.3-flash | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderNaN | Provider model IDglm5.3-flash | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderSCNet Token Plan | Provider model IDGLM-5.3-Flash | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderVolcengine Ark Coding Plan | Provider model IDglm-5.3-flash | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderNvidia | Provider model IDz-ai/glm-5.3-flash | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderUmans AI Coding Plan | Provider model IDumans-glm-5.3-flash | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderAMD | Provider model IDGLM-5.3-Flash | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context262.1K | Updated |
| ProviderOpenRouter | Provider model IDz-ai/glm-5.3-flash | Regionglobal | Input / 1M$0.0052 | Output / 1M$0.1985 | Context1M | Updated |
| ProviderPareto Inference | Provider model IDz-ai/glm-5.3-flash | Regionglobal | Input / 1M$0.06 | Output / 1M$0.20 | Context1M | Updated |
| ProviderEmpirioLabs AI | Provider model IDglm-5-3-flash | Regionglobal | Input / 1M$0.075 | Output / 1M$0.25 | Context1M | Updated |
| Provider302.AI | Provider model IDglm-5.3-flash | Regionglobal | Input / 1M$0.075 | Output / 1M$0.25 | Context1M | Updated |
| ProviderZenMux | Provider model IDz-ai/glm-5.3-flash | Regionglobal | Input / 1M$0.075 | Output / 1M$0.25 | Context1M | Updated |
| ProviderIteraCompute | Provider model IDz-ai/glm-5.3-flash | Regionglobal | Input / 1M$0.08 | Output / 1M$0.28 | Context1M | Updated |
| ProviderNEAR AI Cloud | Provider model IDz-ai/glm-5.3-flash | Regionglobal | Input / 1M$0.08 | Output / 1M$0.50 | Context1M | Updated |
| ProviderStandard Compute | Provider model IDz-ai/glm-5.3-flash | Regionglobal | Input / 1M$0.08 | Output / 1M$0.50 | Context1M | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDglm-5.3-flash | Regionglobal | Input / 1M$0.088 | Output / 1M$0.25 | Context1M | Updated |
| ProviderCortecs | Provider model IDglm-5.3-flash | Regionglobal | Input / 1M$0.10 | Output / 1M$0.35 | Context1M | Updated |
| ProviderNanoGPT | Provider model IDz-ai/glm-5.3-flash | Regionglobal | Input / 1M$0.10 | Output / 1M$0.30 | Context1M | Updated |
| ProviderVultr | Provider model IDglm-5.3-flash | Regionglobal | Input / 1M$0.10 | Output / 1M$0.35 | Context1M | Updated |
| ProviderRunInfra | Provider model IDzai-org/GLM-5.3-Flash | Regionglobal | Input / 1M$0.11 | Output / 1M$0.45 | Context1M | Updated |
| ProviderAIHubMix | Provider model IDglm-5.3-flash | Regionglobal | Input / 1M$0.1127 | Output / 1M$0.3944 | Context1M | Updated |
| ProviderKenari | Provider model IDglm-5-3-flash | Regionglobal | Input / 1M$0.1143 | Output / 1M$0.3429 | Context1M | Updated |
| ProviderMelious | Provider model IDglm-5.3-flash | Regionglobal | Input / 1M$0.1159 | Output / 1M$0.4637 | Context1M | Updated |
| ProviderVolcengine Ark | Provider model IDglm-5-3-flash-260828 | Regionglobal | Input / 1M$0.1188 | Output / 1M$0.4156 | Context1M | Updated |
| ProviderZhipu AI | Provider model IDglm-5.3-flash | Regionglobal | Input / 1M$0.1195 | Output / 1M$0.4183 | Context1M | Updated |
| ProviderVancine | Provider model IDglm-5.3-flash | Regionglobal | Input / 1M$0.12 | Output / 1M$0.40 | Context1M | Updated |
| ProviderBoundless | Provider model IDglm-5.3-flash | Regionglobal | Input / 1M$0.12 | Output / 1M$0.40 | Context1M | Updated |
| ProviderGreenPT | Provider model IDglm-5.3-flash | Regionglobal | Input / 1M$0.1278 | Output / 1M$0.511 | Context1M | Updated |
| Providerengy | Provider model IDglm-5.3-flash | Regionglobal | Input / 1M$0.135 | Output / 1M$0.45 | Context327.7K | Updated |
GLM 5.3 Flash Runtime Performance
Provider-specific output speed and catalog latency for GLM-5.3-Flash. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderFriendliAI | Output Speed44.69 tok/s | Catalog Latency4.15 s | Max Input1M | Max Output131.1K | Updated |
| ProviderDeepInfra | Output Speed15.03 tok/s | Catalog Latency6.11 s | Max Input1M | Max Output1M | Updated |
| ProviderZAI | Output Speed8.35 tok/s | Catalog Latency11.21 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 Flash Specifications
Technical details for the model's default version.
- Version
- GLM-5.3-Flash
- Released
- Aug 26, 2026
- Knowledge cutoff
- Unknown
- Parameters
- 320B
- Context window
- 1M
- Max output
- 1M
- Inputs
- image, text, video
- Outputs
- text
- Open weights
- Yes
- License
- MIT
GLM 5.3 Flash 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-Flash | Released | LLMBoard81.34 | Parameters320B | Context1M | Max output1M | Open weightsYes | LicenseMIT |
Models similar to GLM 5.3 Flash
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
ZA
GLM 5.3
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 Flash?
Key information about GLM 5.3 Flash and its available data.
AI's GLM-5 series, using hybrid sparse and linear attention with mHC. It has MIT-licensed open weights available on Hugging Face.
Data as of 2026-10-22.
FAQ
Common questions about GLM 5.3 Flash.
When was GLM 5.3 Flash released?
GLM 5.3 Flash's default version was released on Aug 26, 2026.
How much does GLM 5.3 Flash cost?
GLM 5.3 Flash's official API price is $0.1195 per million input tokens and $0.4183 per million output tokens via Zhipu AI. The lowest tracked third-party offer starts at $0.0052 input and $0.1985 output via OpenRouter.
Who created GLM 5.3 Flash?
GLM 5.3 Flash was created by Zhipu AI.
What is the context window for GLM 5.3 Flash?
The default version has a 1M token context window.
Is GLM 5.3 Flash open weight?
Yes. The default version is marked as open weight under MIT.
How many API providers offer GLM 5.3 Flash?
80 provider offerings are linked to the default version.