GLM-4.5 (Reasoning) — benchmark results
GLM-4.5 evaluated with reasoning enabled. Provider: Zhipu. Released 2025-07-28. Access: Open.
Unified ELO 1696 ± 23, rank #279 of 1776 rated models, from 39 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| UGI - Writing | 57.34 | Writing Score | 92.4 |
| AA MATH-500 | 97.87 | Accuracy (%) | 90.1 |
| UGI - Natural Intelligence | 46.56 | NatInt Score | 89.5 |
| AA LiveCodeBench | 73.76 | Pass@1 (%) | 85.1 |
| AA MMLU-Pro | 83.51 | Accuracy (%) | 84.3 |
| AA Omniscience - Software Engineering (SWE) - Rust | 66 | Accuracy (%) | 80.6 |
| AA Omniscience - Health | 26.6 | Accuracy (%) | 75.8 |
| AA Omniscience - Software Engineering (SWE) - JavaScript | 40.91 | Accuracy (%) | 72 |
| AA Omniscience - Software Engineering (SWE) - Go | 28 | Accuracy (%) | 71.5 |
| AA Omniscience - Software Engineering (SWE) - TypeScript | 35.56 | Accuracy (%) | 70.6 |
| AA Omniscience - Software Engineering (SWE) - Julia | 24 | Accuracy (%) | 70.4 |
| AA Omniscience - Humanities & Social Sciences | 25.8 | Accuracy (%) | 69.9 |
Interactive version: theaggregate.ai/model?slug=glm-4-5-reasoning · How the rankings work · Data refreshed daily, snapshot 2026-07-22.