Artificial Analysis ranks GLM-5.2 as the top open-weight model on its Intelligence Index

Artificial Analysis has ranked Z.ai’s GLM-5.2 as the leading open-weight model on its Artificial Analysis Intelligence Index.

GLM-5.2 reaches the top open-weight slot

In an article and model analysis page, Artificial Analysis reports that GLM-5.2 Reasoning ranks #1 among 92 models in its open-weight comparison, with an Artificial Analysis Intelligence Index score of 51. The firm describes GLM-5.2 as an open-weight model and lists a 1 million-token context window.

Artificial Analysis’ Intelligence Index is a composite benchmark used by the publisher to compare model capability across its evaluated set. In this case, the reported score places GLM-5.2 ahead of other open-weight models tracked by Artificial Analysis, according to the company’s own ranking page.

Pricing and context window

Artificial Analysis also lists Z.ai’s first-party API pricing for GLM-5.2 at $1.40 per 1 million input tokens, $4.40 per 1 million output tokens, and $0.26 per 1 million cache-hit tokens. Those figures are presented by Artificial Analysis as part of its performance and price analysis for the model.

Z.ai’s official GLM-5.2 documentation separately presents the model as its current language model and emphasizes a usable 1 million-token context window. The company’s documentation also says GLM-5.2 is the highest-ranked open-source model across long-horizon coding benchmarks cited by Z.ai, though that claim should be read as Z.ai’s own framing of benchmark performance.

A 1 million-token context window is significant for use cases that require a model to process long inputs, such as large codebases, lengthy documents, or multi-file analysis. However, benchmark ranking and context length do not by themselves determine suitability for a specific deployment. Latency, reliability, licensing terms, safety requirements, and real-world task performance remain important factors for users comparing models.

Why the ranking matters

The result adds another competitive entry to the open-weight model landscape, where developers and enterprises often weigh transparency, deployability, and cost against the performance of closed commercial models. Artificial Analysis’ ranking gives GLM-5.2 a prominent position in that comparison, particularly for teams tracking open-weight alternatives with long-context capabilities.

The available source material does not establish independent third-party validation beyond Artificial Analysis’ ranking and Z.ai’s own documentation. Still, the combination of a high Intelligence Index score, open-weight availability as described by Artificial Analysis, and published first-party API pricing gives developers concrete data points to evaluate GLM-5.2 against other models.

For now, the clearest source-backed takeaway is that Artificial Analysis places GLM-5.2 at the top of its open-weight Intelligence Index, while Z.ai highlights the model’s long-context design and coding benchmark performance in its official documentation.