LingoQA: Results as Published

LingoQA is a visual question-answering benchmark for driving. The dataset has 28K short video scenarios and 419K free-text annotations, asking what is in the scene, what the vehicle should do next, why, and what deserves attention. The published evaluation suite has 1,000 examples. A learned text classifier, Lingo-Judge, reads the question, a human answer, and the model answer, without seeing the video, and the score is the share of answers it marks correct.

Every number here is read from the same catalog file as the benchmark table, data version 2026103001, and is the number the table shows for that model and test. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.