Automated page. Written and translated automatically by AI and checked against the sources by software; no human editor. SI-IQ is an index built from public benchmark results, not an IQ test. How it works
Z.ai (Zhipu AI) models by SI-IQ
8 models from Z.ai (Zhipu AI) have independent benchmark results in our data. The best ranked is GLM-5.3 with an SI-IQ of 125.
Models
| 1 | GLM-5.3open Z.ai (Zhipu AI) | 125122–128 | 8 |
| 2 | GLM-5.2open Z.ai (Zhipu AI) | 121118–124 | 9 |
| 3 | GLM-5.3-Flashopen Z.ai (Zhipu AI) | 120117–124 | 7 |
| 4 | GLM-5.1open Z.ai (Zhipu AI) | 116112–120 | 7 |
| 5 | GLM-4.7open Z.ai (Zhipu AI) | 112107–118 | 5 |
| 6 | GLM-4.6open Z.ai (Zhipu AI), Tsinghua University | 117106–128 | 3 too little data |
| 7 | GLM-4.5-Airopen Z.ai (Zhipu AI), Tsinghua University | 11491–137 | 1 too little data |
| 8 | GLM-5open Z.ai (Zhipu AI) | 112105–118 | 4 too little data |
Data sources: Aider polyglot leaderboard data (Apache-2.0); Arena leaderboard dataset on Hugging Face (CC BY 4.0); Berkeley Function Calling Leaderboard, Gorilla project (Apache-2.0); Epoch AI, ‘Capabilities & benchmarking’ (CC BY 4.0); API list prices via LiteLLM's price table (MIT); each price links to the developer's pricing page; Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter..