GLM-5.3 (Low): benchmark results
Provider: Zhipu. Released 2026-08-14. Access: API.
Unified ELO 1651 ± 1, rank #217 of 1935 rated models, from 59 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Artificial Analysis Intelligence Index | 34.3 | Intelligence Index | 89.4 |
| AA CritPt | 14.57 | Accuracy (%) | 85.9 |
| AA Humanity's Last Exam | 36.56 | Accuracy (%) | 85.9 |
| AA-Omniscience Index - Software Engineering (SWE) - TypeScript | 34.44 | Omniscience Index | 80.6 |
| AA-Omniscience Index - Software Engineering (SWE) - Kotlin | 20 | Omniscience Index | 79.8 |
| AA-Omniscience Index - Science, Engineering & Mathematics | 0.8 | Omniscience Index | 79.1 |
| AA-Omniscience Index - Software Engineering (SWE) - C | 43 | Omniscience Index | 77.9 |
| AA-Omniscience Index - Software Engineering (SWE) - Swift | 32 | Omniscience Index | 77.2 |
| AA-Omniscience Index - Software Engineering (SWE) - PHP | 18 | Omniscience Index | 76.9 |
| AA-Omniscience Index - Software Engineering (SWE) - R | -2 | Omniscience Index | 76.2 |
| AA-Omniscience Index - Software Engineering (SWE) - Python | 14 | Omniscience Index | 75.9 |
| AutomationBench-AA - Sales - Raw Objective Completion | 76.88 | Raw Objective Completion (%) | 75.8 |
Interactive version: theaggregate.ai/model?slug=glm-5-3-low · How It Works · Data refreshed daily, snapshot 2026-09-25.