Mistral

GLM-5.2 — Benchmark Scores, Pricing & Performance Analysis

OPEN SOURCEMistral
Input Cost
$0.68/1M
Output Cost
$2.1/1M
Context Window
1.0M
Max Output
131K
Accepts
text

GLM-5.2 is an AI model by Mistral. View detailed benchmark scores, pricing data, and performance metrics on Serenities AI Models.

Specifications last checked against the provider on . Benchmark scores carry their own source, linked beside each number.

Coding Benchmarks

Design Arena ELO
129215th of 120

Human preference ELO for building things — websites, UI, games, charts, SVG

Design Arena (via OpenRouter)
AA Coding Index
68.826th of 96

Artificial Analysis composite coding score

Artificial Analysis (via OpenRouter)
Website Arena ELO
130511th of 108

Human preference ELO for building a working web page from a brief

Design Arena (via OpenRouter)

Reasoning Benchmarks

AA Agentic Index
39.421st of 70

Artificial Analysis composite score for multi-step tool-using tasks

Artificial Analysis (via OpenRouter)
GPQA Diamond
85.6%31st of 140

Graduate-level science Q&A by domain experts

Papers
τ²-Bench Airline
74.9%27th of 93

Multi-turn service agent making tool calls under strict policy constraints

OpenRouter (measured)

Cost Benchmarks

Input Cost
$0.68268th of 413

Cost per 1M input tokens

OpenRouter API
Output Cost
$2.1257th of 413

Cost per 1M output tokens

OpenRouter API
Cached Input Cost
$0.1373rd of 136

Cost per 1M cached input tokens — the price that actually applies to a long agent conversation

OpenRouter API

Context Benchmarks

Context Length
1.0M18th of 451

Maximum context window size

OpenRouter API

Available from 86 providers

The same model costs different amounts depending on who serves it. You can bring your own key for 11 of these — connect it here.

ProviderInput / 1MOutput / 1MCached inContextYour key
Alibaba Token Plan$0$0$01.0M
Alibaba Token Plan (China)$0$0$01.0M
Kenari$0$01.0M
Nvidia$0$01.0M
SCNet Token Plan$0$0$01.0M
SenseNova (China)$0$0$01.0M
Umans AI Coding Plan$0$0$0406K
UnoRouter$0$01.0M
Z.AI Coding Plan$0$0$01.0M
ZenMux$0$0$01.0M
Zhipu AI Coding Plan$0$0$01.0M
CrofAI$0.3$1.05$0.051.0M
NanoGPT$0.42$1.32$0.0781.0M
SCX.ai$0.55$1.784$0.1111.0M
Ambient$0.6$2$0.15203K
OpenRouter$0.6832$2.1472$0.126881.0MSupported
DigitalOcean$0.7$2.2$0.105262K
Inceptron$0.71$2.35$0.121.0M
Deep Infra$0.75$2.4$0.141.0MSupported
Weights & Biases$0.76$2.42$0.141.0M
LLM Gateway$0.8$2.55$0.161.0M
routing.run$0.8$2.4200K
Vercel AI Gateway$0.8$2.55$0.161.0MSupported
Vultr$0.85$3.1393K
Lilac$0.9$3$0.27524K
GMI Cloud$0.979$3.08$0.1821.0M
ai&$1$41.0M
Merge Gateway$1.05$3.3$0.1951.0M
Alibaba (China)$1.1$3.851$0.2751.0M
AIHubMix$1.1268$3.9438$0.28171.0M
Volcengine Ark$1.18747$4.15615$0.296871.0M
Cortecs$1.2$4.2$0.261.0M
CrossModel$1.2$4.4$0.31.0M
Requesty$1.2$4.2$0.261.0M
Vivgrid$1.2$4.2$0.31.0M
Wafer$1.2$4.1$0.21.0M
DInference$1.25$3.891.0M
GreenPT$1.254$5.016$0.31351.0M
302.AI$1.4$4.41.0M
Abacus$1.4$4.4$0.261.0M
Alibaba$1.4$4.4$0.281.0MSupported
Arcee$1.4$4.4$0.26262K
Baseten$1.4$4.4$0.31.0MSupported
ClinePass$1.4$4.4$0.261.0M
Cloudflare Workers AI$1.4$4.4$0.26262KSupported
Crusoe$1.4$4.4$0.261.0M
Databricks$1.4$4.4$0.261.0M
Eden AI$1.4$4.4$0.261.0M
EmpirioLabs AI$1.4$4.4$1.41.0M
Fireworks AI$1.4$4.4$0.141.0MSupported
Friendli$1.4$4.4$0.261.0M
HPC-AI$1.4$4.4$0.261.0M
Hugging Face$1.4$4.4262KSupported
Impossibl$1.4$4.4$0.141.0M
Jalapeno Cloud$1.4$4.41.0M
Kilo Gateway$1.4$4.4$0.261.0M
Mistral$1.4$4.4$0.141.0MSupported
Nebius Token Factory$1.4$4.41.0M
Neon$1.4$4.4$0.261.0M
NovitaAI$1.4$4.4$0.261.0M
Ofox$1.4$4.4$0.261.0M
OpenCode Go$1.4$4.4$0.261.0M
OpenCode Zen$1.4$4.4$0.261.0M
OrcaRouter$1.4$4.4$0.261.0M
Pioneer$1.4$4.4$0.261.0M
SiliconFlow$1.4$4.4$0.261.0M
SiliconFlow (China)$1.4$4.4$0.261.0M
Subconscious$1.4$4.4$0.261.0M
Synthetic$1.4$4.4$1.4524K
Together AI$1.4$4.4$0.26512KSupported
TokenGo$1.4$4.4$0.261.0M
Umans AI$1.4$4.4$0.26406K
Venice AI$1.4$4.4$0.261.0M
Z.AI$1.4$4.4$0.261.0M
Zhipu AI$1.4$4.4$0.261.0MSupported
evroc$1.4375$5.75524K
Neuralwatt$1.45$4.5$0.1451.0M
TensorX$1.5$4.5$0.3751.0M
Charm Hyper$1.52432$4.79072$0.1524321.0M
above.dev$1.54$4.84$0.1541.0M
Berget.AI$1.54$4.84524K
Scaleway$1.8$5.5256K
DevPass (LLM Gateway)$2.2$6.5$0.451.0M
Regolo AI$2.31$696K
Model Oracle AI1.0M
Ollama Cloud976K

GLM-5.2 — Benchmark Scores Overview

Scores normalized to percentage scale for visual comparison. ELO scores mapped to 0-100 range (1100-1500).

GLM-5.2 — Frequently Asked Questions

How much does GLM-5.2 cost?

GLM-5.2 costs $0.68 per 1M input tokens and $2.1 per 1M output tokens. This is mid-range pricing for its capability level.

What is the context window of GLM-5.2?

GLM-5.2 has a context window of 1.0M tokens. This determines how much text, conversation history, and code the model can process in a single request.

Who created GLM-5.2?

GLM-5.2 was created by Mistral. It is classified as a open source model in our catalogue.

Is GLM-5.2 open source?

Yes, GLM-5.2 is an open-source model. The model weights are publicly available for download and self-hosting.