Visual Dialog
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
69.35MRR
141
Feb 26, 2026
75.13NDCG
98
May 26, 2026
0.695MRR
75
May 26, 2026
64.1MRR
58
Feb 26, 2026
62.27MRR
36
Feb 26, 2026
0.635MRR
27
Feb 26, 2026
0.993Accuracy
7
Feb 26, 2026
63.5MRR
7
Feb 26, 2026
62.08RAD (Y/N <- C)
2
Feb 26, 2026
68.99Y/N Accuracy (C)
2
Feb 26, 2026