GLM-5.3 (High): benchmark results
Provider: Zhipu. Released 2026-08-14. Access: API.
Unified ELO 1751 ± 1, rank #35 of 3078 rated models, from 9 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AI Coding Daily (OpenCode) - Total | 49.92 | Total points (max 60) | 94.7 |
| DuelLab Overall | 59.4 | DuelLab Score | 92.4 |
| Multi-turn Debate (Lechmazur) | 1653.1 | Bradley-Terry Rating | 90.2 |
| Context Arena | 70.4 | Average Score (%) | 81.9 |
| DeepsecBench | 21.91 | Recall-weighted F2 score (%) | 81.1 |
| AI Coding Daily (OpenCode) - Laravel Code Quality | 17.55 | Laravel Code Quality (max 20) points, LLM-judged rubric scor | 78.9 |
| AI Coding Daily (OpenCode) - React-TS Code Quality | 17.67 | React-TS Code Quality (max 20) points, LLM-judged rubric sco | 71.1 |
| CWE-Bench | 31.1 | Pass@1 (%) | 42.9 |
| MazeBench | 0 | Gems collected (gems) | 37.5 |
Interactive version: theaggregate.ai/model?slug=glm-5-3-high · How It Works · Data refreshed daily, snapshot 2026-09-19.