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
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Guesswork 2026-07 | 0.67 | MAE (z-score units) | 100 |
| LLM Stats (AIME 2026) | 99.2 | Score (%) | 100 |
| MLE-Bench Lite (OpenMLE-Evo) | 62.12 | Medal Average (%) | 100 |
| Spider 2.0-Lite | 76.23 | Accuracy (%) | 100 |
| StructureClaw (Automatic Workflow) | 97.3 | Success Rate (%) | 100 |
| OpenClawProBench | 81.3 | Overall Score (%) | 98.5 |
| Design Arena (Data Viz) | 1318 | Elo | 94.9 |
| LLM Stats (IMO-AnswerBench) | 91 | Score (%) | 94.7 |
| Design Arena (Website) | 1315 | Elo | 94.2 |
| EQ-Bench Creative Writing v3 | 1643.2 | Elo | 93.3 |
| LLM Stats Score | 45.67 | LLM Stats Score (conservative rating) | 92.9 |
| Vending-Bench 2 | 8313.78 | Money Balance ($) | 92.3 |
Interactive version: theaggregate.ai/model?slug=glm-5-2 · How It Works · Data refreshed daily, snapshot 2026-09-05.