GLM-5.2 (High) — benchmark results
Provider: Zhipu. Released 2026-06-13. Access: Open.
Unified ELO 1898 ± 13, rank #69 of 1746 rated models, from 7 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| WeirdML | 67.31 | Average Score | 86 |
| LisanBench | 0.13 | Mean Path Length / Current Maximum | 78.5 |
| Opus Magnum Bench | 25.39 | Human-normalized score (%) | 61.9 |
| Surface Evolver Bench Pass Rate | 31.25 | Pass Rate (%) | 58.8 |
| Surface Evolver Bench | 55.62 | Mean Score (%) | 52.9 |
| Epoch AI - Cursorbench | 50.7 | Score | 29.6 |
| CursorBench 3.1 | 51.5 | Score (%) | 22.6 |
Interactive version: aibenchmarks.dev/model?slug=glm-5-2-high · How the rankings work · Data refreshed daily, snapshot 2026-07-11.