GLM-5 by Zhipu AI demonstrates top-tier general intelligence. View detailed benchmark data including scores across coding, math, reasoning, speed, and cost metrics.
Specifications last checked against the provider on . Benchmark scores carry their own source, linked beside each number.
General Benchmarks
Human preference ELO from blind head-to-head votes
LMSYS / HuggingFaceCoding Benchmarks
Human preference ELO for building things — websites, UI, games, charts, SVG
Design Arena (via OpenRouter)Human preference ELO for building a working web page from a brief
Design Arena (via OpenRouter)Reasoning Benchmarks
Multi-turn service agent making tool calls under strict policy constraints
OpenRouter (measured)Speed Benchmarks
Cost Benchmarks
Cost per 1M cached input tokens — the price that actually applies to a long agent conversation
OpenRouter APIContext Benchmarks
Available from 44 providers
The same model costs different amounts depending on who serves it. You can bring your own key for 9 of these — connect it here.
| Provider | Input / 1M | Output / 1M | Cached in | Context | Your key |
|---|---|---|---|---|---|
| Alibaba Coding Plan | $0 | $0 | $0 | 203K | — |
| Alibaba Coding Plan (China) | $0 | $0 | $0 | 203K | — |
| Alibaba Token Plan | $0 | $0 | $0 | 203K | — |
| Alibaba Token Plan (China) | $0 | $0 | $0 | 203K | — |
| SCNet Token Plan | $0 | $0 | $0 | 205K | — |
| Tencent Coding Plan (China) | $0 | $0 | $0 | 203K | — |
| NanoGPT | $0.5 | $2.55 | $0.13 | 200K | — |
| Alibaba (China) | $0.573 | $2.58 | — | 203K | — |
| ZenMux | $0.58 | $2.6 | $0.14 | 200K | — |
| 302.AI | $0.6 | $2.6 | — | 205K | — |
| CrossModel | $0.6 | $3 | $0.16 | 200K | — |
| Deep Infra | $0.6 | $2.08 | $0.12 | 203K | Supported |
| GMI Cloud | $0.6 | $1.92 | $0.12 | 203K | — |
| Kilo Gateway | $0.6 | $1.92 | $0.12 | 198K | — |
| OpenRouter | $0.6 | $1.92 | $0.12 | 205K | Supported |
| DevPass (LLM Gateway) | $0.72 | $2.3 | $0.144 | 203K | — |
| DInference | $0.75 | $2.4 | — | 200K | — |
| Meganova | $0.8 | $2.56 | — | 203K | — |
| Charm Hyper | $0.86 | $2.752 | $0.43 | 203K | — |
| TokenGo | $0.89 | $3.2647 | $0.2226 | 205K | — |
| Baseten | $0.95 | $3.15 | $0.2 | 203K | Supported |
| FastRouter | $0.95 | $3.15 | — | 205K | — |
| Cortecs | $0.988 | $3.164 | $0.247 | 203K | — |
| Abacus | $1 | $3.2 | — | 205K | — |
| Amazon Bedrock | $1 | $3.2 | — | 203K | Supported |
| DigitalOcean | $1 | $3.2 | $0.2 | 64K | — |
| Eden AI | $1 | $3.2 | $0.2 | 203K | — |
| Hugging Face | $1 | $3.2 | $0.2 | 203K | Supported |
| Impossibl | $1 | $3.2 | $0.2 | 205K | — |
| LLM Gateway | $1 | $3.2 | $0.2 | 203K | — |
| Merge Gateway | $1 | $3.2 | $0.2 | 200K | — |
| NovitaAI | $1 | $3.2 | $0.2 | 203K | — |
| Ofox | $1 | $3.2 | $0.2 | 205K | — |
| OpenCode Go | $1 | $3.2 | $0.2 | 203K | — |
| OpenCode Zen | $1 | $3.2 | $0.2 | 205K | — |
| OrcaRouter | $1 | $3.2 | $0.26 | 205K | — |
| Poe | $1 | $3.2 | $0.2 | 205K | — |
| TensorX | $1 | $3.2 | $0.25 | 203K | — |
| Together AI | $1 | $3.2 | — | 203K | Supported |
| Venice AI | $1 | $3.2 | $0.2 | 198K | — |
| Vercel AI Gateway | $1 | $3.2 | — | 203K | Supported |
| Vertex | $1 | $3.2 | $0.1 | 203K | Supported |
| Z.AI | $1 | $3.2 | $0.2 | 205K | — |
| Zhipu AI | $1 | $3.2 | $0.2 | 205K | Supported |
GLM-5 — Benchmark Scores Overview
Scores normalized to percentage scale for visual comparison. ELO scores mapped to 0-100 range (1100-1500).
Compare GLM-5 With
GLM-5 — Frequently Asked Questions
How intelligent is GLM-5?
GLM-5 scores 1456 on the Chatbot Arena ELO rating, making it one of the top-ranked AI model. This score is based on blind head-to-head human preference voting.
How much does GLM-5 cost?
GLM-5 costs $0.60 per 1M input tokens and $1.9 per 1M output tokens. This is mid-range pricing for its capability level.
How fast is GLM-5?
GLM-5 generates output at 55 tokens per second, which is slower, prioritizing quality over speed compared to other models. The time to first token is 1030 ms.
What is the context window of GLM-5?
GLM-5 has a context window of 205K tokens. This determines how much text, conversation history, and code the model can process in a single request.
Who created GLM-5?
GLM-5 was created by Zhipu AI. It is classified as a flagship model in our catalogue.
Is GLM-5 open source?
No, GLM-5 is a proprietary model. It is available through Zhipu AI's API and compatible providers.