Zhipu AI model product
GLM 4.5
5 is a 355 billion-parameter MoE foundation model from Zhipu AI with 32 billion active parameters, 128K context length, and thinking and non-thinking modes.
Updated Oct 23, 2026. Default version: GLM-4.5
LLMBoard Score47.5GLM-4.5
Coverage100%14 benchmark families
Context window131.1KTokens
Official input price$0.60Zhipu AI API
GLM 4.5 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
GLM 4.5 Benchmark Results
Benchmark scores for GLM-4.5.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkAA-Index | Score67.70% | Rank01 | Participants4 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkBFCL-v3 | Score77.80% | Rank01 | Participants20 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkMATH-500 | Score98.20% | Rank03 | Participants33 | Percentile93.75% | EvidenceC | Evaluated |
| BenchmarkTAU-bench Airline | Score60.40% | Rank04 | Participants23 | Percentile86.36% | EvidenceC | Evaluated |
| BenchmarkTAU-bench Retail | Score79.70% | Rank06 | Participants25 | Percentile79.17% | EvidenceC | Evaluated |
| BenchmarkAIME 2024 | Score91.00% | Rank08 | Participants54 | Percentile86.79% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench | Score37.50% | Rank12 | Participants25 | Percentile54.17% | EvidenceC | Evaluated |
| BenchmarkSciCode | Score41.70% | Rank18 | Participants31 | Percentile43.33% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench | Score72.90% | Rank21 | Participants76 | Percentile73.33% | EvidenceC | Evaluated |
| BenchmarkMMLU-Pro | Score84.60% | Rank28 | Participants142 | Percentile80.85% | EvidenceC | Evaluated |
| BenchmarkAA AIME 2025 | Score73.67% | Rank38 | Participants96 | Percentile61.05% | EvidenceB | EvaluatedN/A |
| BenchmarkBrowseComp | Score26.40% | Rank68 | Participants70 | Percentile2.90% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text | Score1,430.01 rating | Rank73 | Participants218 | Percentile66.82% | EvidenceA | Evaluated |
| BenchmarkAA Omniscience Accuracy | Score25.13% | Rank84 | Participants201 | Percentile58.50% | EvidenceB | EvaluatedN/A |
| BenchmarkSWE-Bench Verified | Score64.20% | Rank86 | Participants120 | Percentile28.57% | EvidenceC | Evaluated |
| BenchmarkHumanity's Last Exam | Score14.40% | Rank88 | Participants109 | Percentile19.44% | EvidenceC | Evaluated |
| BenchmarkAA IFBench | Score44.08% | Rank98 | Participants168 | Percentile41.92% | EvidenceB | EvaluatedN/A |
| BenchmarkAA GPQA Diamond | Score78.18% | Rank105 | Participants199 | Percentile47.47% | EvidenceB | EvaluatedN/A |
| BenchmarkGPQA | Score79.10% | Rank107 | Participants256 | Percentile58.43% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,410.88 rating | Rank110 | Participants218 | Percentile49.77% | EvidenceA | Evaluated |
| BenchmarkAA HLE Text No Tools | Score12.97% | Rank112 | Participants200 | Percentile44.22% | EvidenceB | EvaluatedN/A |
| BenchmarkAA LCR v1.1 | Score52.67% | Rank122 | Participants193 | Percentile36.98% | EvidenceB | EvaluatedN/A |
| BenchmarkAA CritPt | Score0.00% | Rank132 | Participants200 | Percentile34.17% | EvidenceB | EvaluatedN/A |
GLM 4.5 Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext | Categoryspanish | Rank42 | Rating / score1,454.21 | Votes678 | ObservationsN/A | Result date |
| Arenatext | Categoryjapanese | Rank46 | Rating / score1,415.10 | Votes776 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry medicine and healthcare | Rank52 | Rating / score1,454.82 | Votes1,386 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry entertainment and sports and media | Rank64 | Rating / score1,404.38 | Votes4,317 | ObservationsN/A | Result date |
| Arenatext | Categoryexclude ties | Rank71 | Rating / score1,422.56 | Votes16,958 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry legal and government | Rank71 | Rating / score1,437.84 | Votes1,476 | ObservationsN/A | Result date |
| Arenatext | Categorynon english | Rank72 | Rating / score1,417.08 | Votes13,668 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry life and physical and social science | Rank73 | Rating / score1,444.15 | Votes3,861 | ObservationsN/A | Result date |
| Arenatext | Categoryoverall | Rank73 | Rating / score1,430.01 | Votes23,800 | ObservationsN/A | Result date |
| Arenatext style control | Categoryjapanese | Rank73 | Rating / score1,390.25 | Votes776 | ObservationsN/A | Result date |
| Arenatext | Categorychinese | Rank75 | Rating / score1,465.10 | Votes1,785 | ObservationsN/A | Result date |
| Arenatext | Categorypolish | Rank77 | Rating / score1,422.48 | Votes1,675 | ObservationsN/A | Result date |
| Arenatext | Categorykorean | Rank78 | Rating / score1,380.25 | Votes656 | ObservationsN/A | Result date |
| Arenatext style control | Categoryspanish | Rank79 | Rating / score1,431.39 | Votes678 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry business and management and financial operations | Rank80 | Rating / score1,420.18 | Votes4,225 | ObservationsN/A | Result date |
| Arenatext | Categoryenglish | Rank81 | Rating / score1,436.53 | Votes10,120 | ObservationsN/A | Result date |
| Arenatext | Categorycreative writing | Rank82 | Rating / score1,395.17 | Votes3,095 | ObservationsN/A | Result date |
| Arenatext | Categorymath | Rank83 | Rating / score1,427.03 | Votes1,401 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry writing and literature and language | Rank84 | Rating / score1,402.66 | Votes5,302 | ObservationsN/A | Result date |
| Arenatext | Categoryexpert | Rank86 | Rating / score1,433.29 | Votes1,157 | ObservationsN/A | Result date |
| Arenatext | Categoryhard prompts | Rank86 | Rating / score1,429.26 | Votes11,114 | ObservationsN/A | Result date |
| Arenatext | Categoryrussian | Rank86 | Rating / score1,412.89 | Votes1,569 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry mathematical | Rank90 | Rating / score1,430.03 | Votes1,260 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry software and it services | Rank90 | Rating / score1,440.41 | Votes8,090 | ObservationsN/A | Result date |
| Arenatext | Categoryinstruction following | Rank91 | Rating / score1,404.13 | Votes6,166 | ObservationsN/A | Result date |
| Arenatext | Categorygerman | Rank92 | Rating / score1,406.71 | Votes539 | ObservationsN/A | Result date |
| Arenatext style control | Categoryexpert | Rank96 | Rating / score1,444.70 | Votes1,157 | ObservationsN/A | Result date |
| Arenatext | Categoryhard prompts english | Rank97 | Rating / score1,429.34 | Votes4,831 | ObservationsN/A | Result date |
| Arenatext | Categorymulti turn | Rank97 | Rating / score1,414.89 | Votes3,705 | ObservationsN/A | Result date |
| Arenatext | Categorylonger query | Rank98 | Rating / score1,412.41 | Votes5,086 | ObservationsN/A | Result date |
GLM 4.5 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $0.60 input, $2.2 output per 1M
- Official provider
- Zhipu AI
- Lowest third-party
- From $0.286 input, $1.14 output per 1M via 302.AI
- Tracked offerings
- 18
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderModelScope | Provider model IDZhipuAI/GLM-4.5 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context131.1K | Updated |
| Provider302.AI | Provider model IDglm-4.5 | Regionglobal | Input / 1M$0.286 | Output / 1M$1.14 | Context131.1K | Updated |
| ProviderZenMux | Provider model IDz-ai/glm-4.5 | Regionglobal | Input / 1M$0.2911 | Output / 1M$1.16 | Context128K | Updated |
| ProviderNanoGPT | Provider model IDz-ai/glm-4.5 | Regionglobal | Input / 1M$0.30 | Output / 1M$1.3 | Context128K | Updated |
| ProviderQiniu | Provider model IDglm-4.5 | Regionglobal | Input / 1M$0.5797 | Output / 1M$2.32 | Context131.1K | Updated |
| ProviderOrcaRouter | Provider model IDz-ai/glm-4.5 | Regionglobal | Input / 1M$0.60 | Output / 1M$2.2 | Context131.1K | Updated |
| ProviderHugging Face | Provider model IDzai-org/GLM-4.5 | Regionglobal | Input / 1M$0.60 | Output / 1M$2.2 | Context131.1K | Updated |
| ProviderImpossibl | Provider model IDzai/glm-4.5 | Regionglobal | Input / 1M$0.60 | Output / 1M$2.2 | Context131.1K | Updated |
| ProviderJiekou.AI | Provider model IDzai-org/glm-4.5 | Regionglobal | Input / 1M$0.60 | Output / 1M$2.2 | Context131.1K | Updated |
| ProviderOpenRouter | Provider model IDz-ai/glm-4.5 | Regionglobal | Input / 1M$0.60 | Output / 1M$2.2 | Context131.1K | Updated |
| ProviderZ.AI | Provider model IDglm-4.5 | Regionglobal | Input / 1M$0.60 | Output / 1M$2.2 | Context131.1K | Updated |
| ProviderMerge Gateway | Provider model IDzai/glm-4.5 | Regionglobal | Input / 1M$0.60 | Output / 1M$2.2 | Context128K | Updated |
| ProviderZhipu AI | Provider model IDglm-4.5 | Regionglobal | Input / 1M$0.60 | Output / 1M$2.2 | Context131.1K | Updated |
| ProviderVercel AI Gateway | Provider model IDzai/glm-4.5 | Regionglobal | Input / 1M$0.60 | Output / 1M$2.2 | Context128K | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDglm-4.5 | Regionglobal | Input / 1M$0.60 | Output / 1M$2.2 | Context131K | Updated |
| ProviderKilo Gateway | Provider model IDz-ai/glm-4.5 | Regionglobal | Input / 1M$0.60 | Output / 1M$2.2 | Context131.1K | Updated |
| ProviderAbacus | Provider model IDzai-org/GLM-4.5 | Regionglobal | Input / 1M$0.60 | Output / 1M$2.2 | Context131.1K | Updated |
| ProviderTempr Gateway | Provider model IDzai/glm-4.5 | Regionglobal | Input / 1M$0.60 | Output / 1M$2.2 | Context131.1K | Updated |
GLM 4.5 Runtime Performance
Provider-specific output speed and catalog latency for GLM-4.5. Runtime does not affect the capability score.
No runtime data
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
GLM 4.5 Specifications
Technical details for the model's default version.
- Version
- GLM-4.5
- Released
- Jul 28, 2025
- Knowledge cutoff
- Unknown
- Parameters
- 355B
- Context window
- 131.1K
- Max output
- 131.1K
- Inputs
- text
- Outputs
- text
- Open weights
- Yes
- License
- MIT
GLM 4.5 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-4.5 | Released | LLMBoard47.53 | Parameters355B | Context131.1K | Max output131.1K | Open weightsYes | LicenseMIT |
Models similar to GLM 4.5
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
ZA
GLM 4.6
Zhipu AI
ZA
GLM 5V Turbo
Zhipu AI
ZA
GLM 4.5 Air
Zhipu AI
ZA
GLM 4.7
Zhipu AI
ZA
GLM 4.7 Flash
Zhipu AI
ZA
GLM 5
Zhipu AI
What is GLM 4.5?
Key information about GLM 4.5 and its available data.
5 is an Agentic, Reasoning, and Coding (ARC) foundation model designed for intelligent agents, with support for complex reasoning, tool usage, coding, and immediate responses. 2 across 12 industry-standard benchmarks, and is released under the MIT open-source license.
Data as of 2026-10-22.
FAQ
Common questions about GLM 4.5.
When was GLM 4.5 released?
GLM 4.5's default version was released on Jul 28, 2025.
How much does GLM 4.5 cost?
GLM 4.5's official API price is $0.60 per million input tokens and $2.2 per million output tokens via Zhipu AI. The lowest tracked third-party offer starts at $0.286 input and $1.14 output via 302.AI.
Who created GLM 4.5?
GLM 4.5 was created by Zhipu AI.
What is the context window for GLM 4.5?
The default version has a 131.1K token context window.
Is GLM 4.5 open weight?
Yes. The default version is marked as open weight under MIT.
How many API providers offer GLM 4.5?
18 provider offerings are linked to the default version.