GLM-5.1 (Non-reasoning) — benchmark results
GLM-5.1 evaluated with reasoning disabled. Provider: Zhipu. Released 2026-03-27. Access: Open.
Unified ELO 1742 ± 44, rank #209 of 1776 rated models, from 35 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA TAU-2 Bench | 97.08 | Accuracy (%) | 97.3 |
| UGI - Writing | 54.9 | Writing Score | 91.4 |
| UGI - Natural Intelligence | 49.51 | NatInt Score | 90.8 |
| AA Humanity's Last Exam | 25.63 | Accuracy (%) | 85.5 |
| AA Omniscience - Software Engineering (SWE) - HTML | 58 | Accuracy (%) | 85.3 |
| Artificial Analysis Intelligence Index | 35.37 | Intelligence Index | 84 |
| AA Terminal-Bench Hard | 35.61 | Accuracy (%) | 82 |
| AA GPQA Diamond | 83.94 | Accuracy (%) | 80.6 |
| AA Omniscience - Software Engineering (SWE) - PHP | 42 | Accuracy (%) | 77 |
| AA Omniscience - Software Engineering (SWE) - Python | 33 | Accuracy (%) | 74.1 |
| AA Omniscience - Software Engineering (SWE) - JavaScript | 41.82 | Accuracy (%) | 73.7 |
| AA Omniscience - Software Engineering (SWE) - C | 54 | Accuracy (%) | 73.5 |
Interactive version: theaggregate.ai/model?slug=glm-5-1-non-reasoning · How the rankings work · Data refreshed daily, snapshot 2026-07-22.