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 1691 ± 1, rank #64 of 1392 rated models, from 270 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Guesswork 2026-070.67MAE (z-score units)100
LLM Stats (AIME 2026)99.2Score (%)100
MLE-Bench Lite (OpenMLE-Evo)62.12Medal Average (%)100
Spider 2.0-Lite76.23Accuracy (%)100
StructureClaw (Automatic Workflow)97.3Success Rate (%)100
OpenClawProBench81.3Overall Score (%)98.5
Design Arena (Data Viz)1318Elo94.9
LLM Stats (IMO-AnswerBench)91Score (%)94.7
Design Arena (Website)1315Elo94.2
EQ-Bench Creative Writing v31643.2Elo93.3
LLM Stats Score45.67LLM Stats Score (conservative rating)92.9
Vending-Bench 28313.78Money Balance ($)92.3

Interactive version: theaggregate.ai/model?slug=glm-5-2 · How It Works · Data refreshed daily, snapshot 2026-09-05.