GLM-5.2 (High): benchmark results
GLM-5.2 evaluated at the high reasoning-effort setting. Provider: Zhipu. Released 2026-06-13. Access: Open.
Unified ELO 1681 ± 1, rank #150 of 1761 rated models, from 12 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SWE-rebench | 57.01 | Resolved (%) | 83.3 |
| WeirdML | 67.31 | Average Score | 80.9 |
| LisanBench | 0.12 | Mean Path Length / Current Maximum | 77.1 |
| E-Commerce Bench | 301 | Final Assets (¥k, mean of 5 episodes) | 70.6 |
| Opus Magnum Bench | 25.39 | Human-normalized score (%) | 61.9 |
| OckBench | 78.5 | Accuracy (%) | 58.2 |
| Computer Anthology Terminal Tasks (Terminus-2) | 31.4 | pass@1 (%) | 53.8 |
| Surface Evolver Bench Pass Rate | 31.25 | Pass Rate (%) | 52 |
| Surface Evolver Bench | 55.62 | Mean Score (%) | 48 |
| CursorBench 3.1 | 51.5 | Score (%) | 23.3 |
| Aikido CVE Rediscovery (pass@3) | 50 | Recall (%) | 2.2 |
| Aikido CVE Rediscovery | 37.2 | Recall (%) | 0 |
Interactive version: theaggregate.ai/model?slug=glm-5-2-high · How It Works · Data refreshed daily, snapshot 2026-09-05.