GPT-4o: Visual perception performance of multimodal large language models in piglet activity understanding

Benchmark Model Rank Results
mmr-total-on-mrr-benchmarkGPT-4oTotal Column Score: 457
zero-shot-video-question-answer-on-video-mmeGPT-4oAccuracy (%): 70.3
zero-shot-video-question-answer-on-video-mmeGPT-4o miniAccuracy (%): 62.3
zero-shot-video-question-answer-on-video-mme-1GPT-4oAccuracy (%): 77.2
zero-shot-video-question-answer-on-video-mme-1GPT-4o miniAccuracy (%): 68.9
zero-shot-video-question-answer-on-zero-shotGPT-4oAccuracy (% ): 64.0