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
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LLM Stats (Claw-Eval) | 75 | Score (%) | 91.7 |
| LLM Stats (SimpleVQA) | 78.2 | Score (%) | 91.7 |
| Design Arena (Game Dev) | 1280 | Elo | 83.2 |
| BenchLM | 63.5 | Overall Score | 81.7 |
| Chatbot Arena (Text) | 1437 | Elo | 81 |
| Design Arena (Website) | 1256 | Elo | 77.6 |
| AA-LCR | 61 | Score (self-reported) | 77.4 |
| Design Arena (3D) | 1268 | Elo | 76.9 |
| MineExplorer | 19.93 | Overall TSR (self-reported) | 76.5 |
| Design Arena (UI Components) | 1253 | Elo | 74.3 |
| Design Arena (Data Viz) | 1237 | Elo | 71.7 |
| CritPt | 0.6 | Accuracy (self-reported) | 71.1 |
Interactive version: theaggregate.ai/model?slug=glm-5v-turbo · How the rankings work · Data refreshed daily, snapshot 2026-07-22.