modelgrep
Z

Z.ai: GLM 5 Turbo

z-ai/glm-5-turbo

21st smartest of 178ReasoningToolsJSON
Use via OpenRouter ↗
Intelligence
46.8
21st of 178
Design Elo
1337
3D
Speed
21
258th fastest
Latency
1.6s
first token
Input price
$1.20
216th cheapest
Context
262K
131K max out

How it compares

Smarter than88%
of all ranked models
Faster than13%
of all ranked models
Cheaper than28%
of all ranked models

Overview

GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows...

Benchmarks

independent · via OpenRouter
Artificial Analysis86th percentile
Intelligence Index
46.8
Coding Index
36.8
Agentic Index
66.1
GPQA Diamond
85%
Humanity's Last Exam
25%
SciCode
44%
Tau²-Bench (agentic)
99%
Design Arena · Elo10,563 tournaments
3D
1337
Game Dev
1335
codecategories
1325
UI Component
1321
Website
1320
Data Viz
1307
svg
1269
asciiart
1189

Providers & pricing (1)

ProviderIn $/MOut $/MUptime
AtlasCloudfp8$1.20$4.00100%

Specifications

Context window262K
Max output131K
Knowledge cutoff
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price$0.240/M
ModeratedNo

GLM 5 Turbo FAQ

How much does GLM 5 Turbo cost?

GLM 5 Turbo costs $1.20 per million input tokens and $4.00 per million output tokens via OpenRouter, making it 216th cheapest of 298 paid models.

How smart is GLM 5 Turbo?

GLM 5 Turbo scores 46.8 on the Artificial Analysis Intelligence Index, ranking 21st of 178 benchmarked models, with a GPQA Diamond score of 85%.

How fast is GLM 5 Turbo?

GLM 5 Turbo generates around 21 tokens per second with 1.6s time-to-first-token (p50), the 258th fastest tracked model.

What is GLM 5 Turbo's context window?

GLM 5 Turbo supports a 262K-token context window and can output up to 131K tokens. It accepts text input.

Compare head-to-head