Tanawpamana: Benchmarking Vision-Language Models on Philippine Cultural Heritage Sites

We also introduce the Tanawpamana Benchmark, comprising 4,046 tasks designed to evaluate models' recognition and knowledge of heritage sites. It comes from a paper posted to arXiv on 15 October 2026. Vision-language models are increasingly used to identify and describe places, yet their recognition and knowledge of specific cultures remain poorly understood, particularly in underrepresented regions such as the Philippines. This study introduces the Tanawpamana Dataset, a repository of Philippine heritage site images with metadata based on the Talapamana registry of the National Commission for Culture and the Arts of the Philippines. Evaluating seven vision-language models, we find that they struggle more with fine-grained visual discrimination among similar heritage sites than with coarse recognition, and that their geographic knowledge is weaker when inferred from image inputs than from text.

Why it counts

We also introduce the Tanawpamana Benchmark, comprising 4,046 tasks designed to evaluate models' recognition and knowledge of heritage sites.

Sources

Primary source: primary source

What is not known

This brief does not claim independent replication. Claims that appear only on X and not in the primary source stay unknown.