September 17, 2026
The PRC-based company Z.ai (formerly known as Zhipu AI) released a new AI model, GLM-5.3, on August 14, 2026. Z.ai publicly released the model’s weights two weeks later. In CAISI’s assessment of GLM-5.3’s cyber capabilities, the key findings were:
- GLM-5.3 is the most cyber-capable open-weight model released to date.
- GLM-5.3’s cyber capabilities are significantly lower than those of current U.S. frontier models. GLM-5.3 lags the capability level of the U.S. frontier by about four months in an aggregate measure of performance across CAISI cyber benchmarks.
CAISI evaluated GLM-5.3’s performance on four benchmarks covering vulnerability discovery and exploit development:
| Benchmark | GLM-5.3 | U.S. frontier best | PRC frontier best |
|---|---|---|---|
| SEC-Bench Pro | 40.4% (74/183) | 90.2% (165/183) | 27.3% (50/183) |
| ExploitBench | 61.1% (9.8/16) | 100.0% (16.0/16) | 32.2% (5.1/16) |
| ExploitGym (Userspace) | 9.4% (47/498) | 44.4% (223/502) | 2.6% (13/502) |
| OSS-Fuzz | 7.7% (23/297) | 23.2% (69/297) | 2.4% (7/297) |
The “Current U.S. Frontier” data point represents the highest cyber capability level among released U.S. models. GLM-5.3’s cyber capability index is higher than Kimi K3 and lower than the current U.S. frontier and other recent U.S. frontier models.