Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Multi-modal Evaluation on DEMON Benchmark (zero-shot)

37.5Multi Modal Dialogue

VPG-C

6.601614.623322.64530.6667Aug 22, 2024
Updated 3d ago

Evaluation Results

MethodLinks
2024.08
37.525.225.922.1548.644.9350.28
2024.08
34.6321.5330.2433.3551.5347.3354.38
2024.08
33.5824.4111.4921.247.444.448.55
2024.08
27.1714.3211.6231.6546.438.8744.58
2024.08
16.8824.2213.8521.653230.641.63
2024.08
15.3715.5711.391641.6727.7343.85
2024.08
14.2217.5713.511844.83244.03
2024.08
13.717.077.9516.630.2726.443.5
2024.08
12.6719.335.416.2533.2732.4742.5
2024.08
11.9620.13.6718.2539.7330.5339.53
2024.08
7.7910.78.2715.8536.228.3341.53