GLM-5 (Non-reasoning) — benchmark results
GLM-5 evaluated with reasoning disabled. Provider: Zhipu. Released 2026-02-12. Access: Open.
Unified ELO 1661 ± 33, rank #344 of 1776 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 | 90.6 |
| UGI - Writing | 49.22 | Writing Score | 88.6 |
| AA Terminal-Bench Hard | 39.39 | Accuracy (%) | 86.5 |
| CLEM TextMapWorld SpecificRoom | 100 | Game Clemscore (%) | 81.7 |
| Artificial Analysis Intelligence Index | 32.41 | Intelligence Index | 79 |
| AA Omniscience | -11.23 | Score | 77.6 |
| AA Omniscience - Software Engineering (SWE) - Go | 32 | Accuracy (%) | 76.8 |
| AA Omniscience - Software Engineering (SWE) - Python | 34.5 | Accuracy (%) | 75.7 |
| AA Omniscience - Software Engineering (SWE) - PHP | 40 | Accuracy (%) | 75 |
| AA Omniscience - Software Engineering (SWE) - C | 55 | Accuracy (%) | 74.3 |
| CLEM TextMapWorld | 81 | Game Clemscore (%) | 73.3 |
Interactive version: theaggregate.ai/model?slug=glm-5-non-reasoning · How the rankings work · Data refreshed daily, snapshot 2026-07-22.