GLM-5.2 (Reasoning): benchmark results
Provider: Zhipu. Released 2026-06-13. Access: Open.
Unified ELO 1652 ± 1, rank #241 of 1761 rated models, from 8 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| UGI Leaderboard | 58.91 | UGI Score | 98.4 |
| UGI - Writing | 67.03 | Writing Score | 96.9 |
| Wolfram LLM Benchmarking Project | 63.8 | Correct Functionality (%) | 92.5 |
| UGI - Natural Intelligence | 55.21 | NatInt Score | 92 |
| GRIPS | 89.2 | Accuracy (%) | 65.4 |
| GRIPS-hard | 54 | Accuracy (%) | 65.4 |
| SpeechMap Compliance | 52.6 | % Requests Completed | 35.9 |
| UGI - Willingness (W/10) | 2.8 | W/10 Score | 20.6 |
Interactive version: theaggregate.ai/model?slug=glm-5-2-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-05.