Benchmark

BC-VL

BC-VL is a vision-language benchmark for knowledge-grounded multimodal question answering.

Modality
multimodal
Categories
multimodal, knowledge, vision
Openness
unknown
Source
llm_stats
Reported scores
1

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
Qwen3.7-PlusQwen0.5112026-05-31evidence

Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.