GLM-5.2 — benchmark results
Zhipu's flagship GLM-5.2 model for reasoning, coding, and agentic tasks. Provider: Zhipu. Released 2026-06-13. Access: Open.
Unified ELO 1837 ± 12, rank #109 of 1776 rated models, from 144 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Guesswork | 0.66 | MAE (z-score units) | 100 |
| LLM Stats (AIME 2026) | 99.2 | Score (%) | 100 |
| LLM Stats (NL2Repo) | 48.9 | Score (%) | 100 |
| Tau3-Bench Airline | 87.5 | Pass@1 (%) | 100 |
| Tau3-Bench Retail | 85.7 | Pass@1 (%) | 100 |
| Tau3-Bench Telecom | 99.3 | Pass@1 (%) | 100 |
| Design Arena (Website) | 1338 | Elo | 98.7 |
| Design Arena (Game Dev) | 1350 | Elo | 98.6 |
| OpenClawProBench | 81.3 | Overall Score (%) | 98.5 |
| Design Arena (3D) | 1352 | Elo | 97.7 |
| CritPt | 16.7 | Accuracy (self-reported) | 96.9 |
| Design Arena (UI Components) | 1335 | Elo | 96.3 |
Interactive version: theaggregate.ai/model?slug=glm-5-2 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.