GLM-5 (Non-reasoning): benchmark results
GLM-5 evaluated with reasoning disabled. Provider: Zhipu. Released 2026-02-12. Access: Open.
Unified ELO 1575 ± 1, rank #533 of 1761 rated models, from 71 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA TAU-2 Bench | 97.37 | Accuracy (%) | 97.5 |
| UGI - Natural Intelligence | 49.38 | NatInt Score | 89.9 |
| UGI - Writing | 49.22 | Writing Score | 87.9 |
| AA Omniscience - Software Engineering (SWE) - PHP | 42 | Accuracy (%) | 87.2 |
| AA Omniscience - Software Engineering (SWE) - Python | 35.5 | Accuracy (%) | 87 |
| AA Omniscience - Software Engineering (SWE) - C | 55 | Accuracy (%) | 86.7 |
| AA Terminal-Bench Hard | 39.39 | Accuracy (%) | 86.5 |
| AA Omniscience - Software Engineering (SWE) - Go | 32 | Accuracy (%) | 85.5 |
| CLEM TextMapWorld SpecificRoom | 100 | Game Clemscore (%) | 81.7 |
| AA Omniscience - Software Engineering (SWE) - Java | 22 | Accuracy (%) | 79.5 |
| AA Omniscience - Software Engineering (SWE) - HTML | 42 | Accuracy (%) | 78.3 |
| AA Omniscience - Software Engineering (SWE) - TypeScript | 31.11 | Accuracy (%) | 77.1 |
Interactive version: theaggregate.ai/model?slug=glm-5-non-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-05.