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 1860 ± 15, rank #101 of 1749 rated models, from 122 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Design Arena (3D)1370Elo100
LLM Stats (AIME 2026)99.2Score (%)100
LLM Stats (NL2Repo)48.9Score (%)100
OpenClawProBench81.3Overall Score (%)100
Tau3-Bench Airline87.5Pass@1 (%)100
Tau3-Bench Retail85.7Pass@1 (%)100
Tau3-Bench Telecom99.3Pass@1 (%)100
Design Arena (Website)1345Elo99.3
Design Arena (Game Dev)1354Elo98.6
Design Arena (UI Components)1346Elo97.7
CritPt16.7Accuracy (self-reported)96.9
Design Arena (Data Viz)1317Elo96.6

Interactive version: aibenchmarks.dev/model?slug=glm-5-2 · How the rankings work · Data refreshed daily, snapshot 2026-07-14.