GLM-4 32B — benchmark results
Zhipu's open GLM-4 32B model (0414 release). Provider: Zhipu. Released 2025-04-14. Access: Open.
Unified ELO 1586 ± 49, rank #513 of 1776 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| VisualWebArena | 48.7 | Success Rate (%) | 93.5 |
| SuiChat-CN | 74.7 | Standard F1 (self-reported) | 93 |
| SWE-Arena | 1002 | Elo Score | 80.6 |
| EHRBench | 66.12 | Overall Acc (%) (self-reported) | 78.3 |
| Benchmarking Large Language Models for Graphem | 35.62 | Direct (self-reported) | 77.8 |
| Wolfram LLM Benchmarking Project | 40.9 | Correct Functionality (%) | 50.4 |
| Active Evidence-Seeking and Diagnostic Reasoni | 35.7 | Task 2: Active Seeking Exact Accuracy (self-reported) | 42.9 |
| AI Chess Leaderboard (Continuation) | 514 | Elo | 39.9 |
| AsyncTool | 15.17 | Overall (self-reported) | 33.3 |
| Kagi LLM Benchmark | 42.3 | Accuracy (%) | 27.9 |
| Creative Writing v3 | 1143.4 | Elo score (self-reported) | 25.7 |
| EQ-Bench Creative Writing v3 | 996.2 | Elo | 25 |
Interactive version: theaggregate.ai/model?slug=glm-4-32b · How the rankings work · Data refreshed daily, snapshot 2026-07-22.