GLM-4.5 (Reasoning): benchmark results
GLM-4.5 evaluated with reasoning enabled. Provider: Zhipu. Released 2025-07-28. Access: Open.
Unified ELO 1564 ± 1, rank #584 of 1761 rated models, from 40 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| UGI - Writing | 57.34 | Writing Score | 91.7 |
| UGI - Natural Intelligence | 46.56 | NatInt Score | 88.9 |
| AA Omniscience - Software Engineering (SWE) - Rust | 62 | Accuracy (%) | 84 |
| AA Omniscience - Software Engineering (SWE) - Go | 30.61 | Accuracy (%) | 83.1 |
| AA MATH-500 | 97.87 | Accuracy (%) | 82 |
| AA MMLU-Pro | 83.51 | Accuracy (%) | 81.8 |
| AA Omniscience - Software Engineering (SWE) - C | 49.49 | Accuracy (%) | 80.5 |
| AA Omniscience - Software Engineering (SWE) - Kotlin | 28 | Accuracy (%) | 80.5 |
| AA Omniscience - Software Engineering (SWE) - Julia | 24 | Accuracy (%) | 80.2 |
| AA LiveCodeBench | 73.76 | Pass@1 (%) | 80 |
| AA Omniscience - Software Engineering (SWE) - R | 20 | Accuracy (%) | 79.5 |
| AA Omniscience - Software Engineering (SWE) - TypeScript | 33.33 | Accuracy (%) | 79.4 |
Interactive version: theaggregate.ai/model?slug=glm-4-5-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-05.