Running
1
Pisa Bench Leaderboard
🏃
Display model scores across languages
None defined yet.
This is the organization of Pisa-Bench, a benchmark for evaluating vision-language models using the PISA Index. In this organization, we release the benchmark and leaderboard for the evaluation of vision-language models (WIP 👷).
This work is done in collaboration with DFKI and Humboldt-Universität zu Berlin.