Z.ai
GLM-5.3: Frontier Coding with Emergent Cyber Capabilities — evaluation table · 14 August 2026
| Rank | Model | Score (score) |
|---|---|---|
| 1 | GLM 5.3 | 1,769 |
| 8 | GLM 5.2 | 1,508 |
| 5 | Kimi K3 | 1,682 |
| 6 | DeepSeek V4 Pro | 1,590 |
| 3 | Qwen3.8 Max | 1,739 |
| 7 | Claude Opus 4.8 | 1,588 |
| 2 | Claude Fable 5 | 1,743 |
| 4 | GPT-5.6 Sol | 1,730 |
Ranks compare reported scores in the same published row; ties share a rank.
GDPval-AA v2. A raw score, not a percentage. This is version 2; version 2.1 has its own page on this site.
The comparison table Z.ai publishes with GLM-5.3, read on the model card itself. Z.ai states that GLM-5.3 uses the same base model as GLM-5.2 and that every gain comes from post-training, so the GLM-5.2 column is the same architecture one training round earlier. Column names were restated in the form this site uses, and Z.ai labels its own Fable column "Fable 5 (w/ fallback)", which is recorded here as Claude Fable 5 and is the only column whose runs used a fallback model. Rows whose scale is not a percentage keep their own unit: ExploitGym is reported as tasks completed with a 2-hour and a 6-hour budget and is split into two rows so both numbers stay readable, and GDPval-AA v2 is a score rather than a percentage. The table is the only source for several benchmarks on this site, and nothing in it is an independent run.