GLM-4.5 (Non-reasoning): benchmark results
Provider: Zhipu. Released 2025-07-28. Access: Open.
Unified ELO 1608 ± 1, rank #580 of 3078 rated models, from 22 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| UGI Leaderboard | 58.64 | UGI Score | 98.3 |
| ReLE - Agents - BFCL-V3 | 70.8 | Accuracy (%) | 90.3 |
| UGI - Writing | 54.18 | Writing Score | 90.1 |
| ReLE - Agents and Tool Use | 67.9 | Accuracy (%) | 88.7 |
| UGI - Natural Intelligence | 38.72 | NatInt Score | 85.8 |
| ReLE - Education - Primary School Subjects | 60.7 | Accuracy (%) | 61.5 |
| ReLE - Reasoning - BBH | 79.5 | Accuracy (%) | 55.1 |
| ReLE - Education - Gaokao | 46.4 | Accuracy (%) | 48.3 |
| ReLE - Overall | 61.8 | Accuracy (%) | 46 |
| ReLE - Medicine - Physician Exams | 78.5 | Accuracy (%) | 42.1 |
| ReLE - Education | 45.2 | Accuracy (%) | 40.4 |
| ReLE - Language and Instruction Following | 61.6 | Accuracy (%) | 39.9 |
Interactive version: theaggregate.ai/model?slug=glm-4-5-non-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-19.