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 1715 ± 22, rank #250 of 1776 rated models, from 31 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
LLM Stats (Claw-Eval)75Score (%)91.7
LLM Stats (SimpleVQA)78.2Score (%)91.7
Design Arena (Game Dev)1280Elo83.2
BenchLM63.5Overall Score81.7
Chatbot Arena (Text)1437Elo81
Design Arena (Website)1256Elo77.6
AA-LCR61Score (self-reported)77.4
Design Arena (3D)1268Elo76.9
MineExplorer19.93Overall TSR (self-reported)76.5
Design Arena (UI Components)1253Elo74.3
Design Arena (Data Viz)1237Elo71.7
CritPt0.6Accuracy (self-reported)71.1

Interactive version: theaggregate.ai/model?slug=glm-5v-turbo · How the rankings work · Data refreshed daily, snapshot 2026-07-22.