Model

CogVLM-Chat

Vendor N/A

Multimodal

Multimodal
BenchmarkScoreMetricHarnessSourceConfidenceLink
IllusionVQA38.2accuracyN/AIndependentmediumarxiv.org
InfiMM-Eval37.2overall_scoreN/AIndependentmediumarxiv.org
MM-Vet v245.1gpt-4_scoreN/AIndependentmediumarxiv.org
REBUS0.9accuracyN/AIndependentmediumarxiv.org

Reproduced by the community

Loading community runs…