GLM-5V Turbo: benchmark results

Zhipu's GLM-5V Turbo native multimodal vision-coding model for design-to-code and agentic workloads. Provider: Zhipu. Released 2026-04-01. Access: API.

Unified ELO 1651 ± 1, rank #127 of 1392 rated models, from 85 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
LLM Stats (Claw-Eval)75Score (%)92.3
LLM Stats (SimpleVQA)78.2Score (%)92.3
SuperCLUE-AdsVU - Placement Feasibility90.35Score85.7
Chatbot Arena (Text - English)1452Arena Score81
Chatbot Arena (Text - Math)1443Arena Score81
SnakeBench28.1TrueSkill Rating80.8
Chatbot Arena (Text - Coding)1490Arena Score79.6
Chatbot Arena (Text - Chinese)1478Arena Score77.8
SuperCLUE-Ondevice - Text Understanding93.05Score77.8
Chatbot Arena (Text - Instruction Following)1423Arena Score76.9
MineExplorer19.93Overall TSR (self-reported)76.5
Chatbot Arena (Text)1433Elo76.4

Interactive version: theaggregate.ai/model?slug=glm-5v-turbo · How It Works · Data refreshed daily, snapshot 2026-09-05.