GLM-5.2 (Non-reasoning): benchmark results
GLM-5.2 evaluated with reasoning disabled. Provider: Zhipu. Released 2026-06-13. Access: Open.
Unified ELO 1606 ± 1, rank #408 of 1761 rated models, from 25 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| UGI - Writing | 61.21 | Writing Score | 93.5 |
| UGI - Natural Intelligence | 54.88 | NatInt Score | 91.9 |
| AA Omniscience | -6.57 | Score | 76.4 |
| Artificial Analysis Intelligence Index | 26.45 | Intelligence Index | 75.2 |
| AA CritPt | 3.14 | Accuracy (%) | 74.6 |
| AA GDPval | 1311.7 | ELO | 72.2 |
| FrontierMath - Tiers 1-3 (v2) | 42.46 | Accuracy (%, 285 private v2 problems) | 62.2 |
| AA Omniscience - Software Engineering (SWE) | 31.5 | Accuracy (%) | 60 |
| AA Omniscience - Law | 13.4 | Accuracy (%) | 57.2 |
| AA Humanity's Last Exam | 9.78 | Accuracy (%) | 53.2 |
| Epoch AI - Mystery Game Puzzles | 18 | Score | 52.8 |
| AA Omniscience - Humanities & Social Sciences | 20.6 | Accuracy (%) | 51.7 |
Interactive version: theaggregate.ai/model?slug=glm-5-2-non-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-05.