Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Object Hallucination Evaluation on CHAIR

57CHAIRi Score

Greedy

8.43221.04133.6546.259Mar 26, 2026Apr 10, 2026Apr 26, 2026May 12, 2026May 28, 2026Jun 13, 2026Jun 29, 2026
Updated 25d ago

Evaluation Results

MethodLinks
2026.03
57--70.4---16.7-
2026.03
56.2--71.4---14.7-
2026.03
55.6--76.7---16-
2026.03
55.3--73---17-
2026.03
53--76.7---15.2-
2026.03
52.2--76.6---13.5-
2026.03
50.2--74---14-
2026.03
50--78.8---13.6-
2026.03
49.2--78.4---12.9-
2026.03
48--80.2---12.7-
2026.04
32.1----60.1-88-
2026.04
25.9----61.4-70-
2026.04
24.2------55.6-
2026.05
23.5----65-47.470.8
2026.05
23.5----64.9-47.270.6
2026.04
22.5------50.2-
2026.04
21.7----64.3-64-
2026.04
19.8----70.7-54-
2026.03
17.5------58.6-
2026.04
16.8----70.9-54.6-
2026.04
16.7------52.3-
2026.05
16.3--16.336.3--56.2-
2026.04
16.2----70.7-48.8-
2026.04
16.2----73.2-52-
2026.04
16.2----73.2-52-
2026.04
16.1----71.5-52.4-
2026.04
15.8----68.2-48.2-
2026.05
15.8----76.5-52.872.6
2026.04
15.6------50.2-
2026.04
15.6------50.2-
2026.05
15.4--77.132.7--50-
2026.04
14.9----71.3-46.2-
2026.04
14.9------48.5-
2026.05
14.9--77.331.8--48.6-
2026.05
14.7----77.4-51.873.7
2026.05
14.6--76.831.2--47.8-
2026.04
14.5----72.2-47.2-
2026.04
14.5------46.8-
2026.04
14.4----74.8-46-
2026.06
14.4------35-
2026.04
14.3------46.2-
2026.05
14.3--37.616.3--18.4-
2026.05
14.17-----88.7252.5-
2026.04
14.1----70.7-44.6-
2026.04
13.9------48-
2026.04
13.9------48-
2026.04
13.9------53-
2026.04
13.9------53-
2026.05
13.8--79.630.7--47.6-
2026.05
13.8----75.7-49.876
2026.04
13.7------46.8-
2026.05
13.7-----93.2852.1-
2026.04
13.6------47.7-
2026.05
13.52-----82.6648.6-
2026.04
13.5----74.4-44.2-
2026.04
13.5----73.1-48.8-
2026.05
13.47-----85.9348.4-
2026.05
13.42-----89.4448.9-
2026.04
13.4------47.3-
2026.05
13.34-----78.3448.2-
2026.04
13.3----74.2-45-
2026.05
13.28-----89.3849.8-
2026.05
13.27-----89.7446.4-
2026.05
13.23-----95.8547.8-
2026.04
13.2------46.8-
2026.04
13.2------41.6-
2026.04
13.2------41.6-
2026.04
13----66-46-
2026.04
12.9------44.8-
2026.04
12.9----66.4-44-
2026.04
12.8----70-35.2-
2026.04
12.7------45.2-
2026.04
12.6----66.5-31.6-
2026.05
12.6--76.727.7--42.8-
2026.06
12.6------36.2-
2026.04
12.5----70.4-35.6-
2026.03
12.3------43.8-
2026.05
12.3--47.912.6--13-
2026.06
12.3------37.2-
2026.04
11.8----70.5-34.2-
2026.04
11.8----75.3-41-
2026.05
11.8--77.626.2--40.6-
2026.03
11.7------36.6-
2026.04
11.7----70.7-35.4-
2026.05
11.7----68.8-38.479.5
2026.04
11.5----75-37.8-
2026.04
11.5----74.8-38-
2026.06
11.4------29.8-
2026.04
11.3----71-32.2-
2026.04
11.2----72.3-29.8-
2026.04
11.2----71.4-31.6-
2026.04
11.2------39.7-
2026.04
11.2------39.7-
2026.04
10.7----71.5-27.8-
2026.04
10.7----75.2-33.8-
2026.04
10.7----68.8-28.8-
2026.04
10.7----70-27.8-
2026.04
10.5----66.7-20.8-
2026.04
10.4----71.8-30.2-
2026.04
10.3----67-21.8-
Showing 100 of 316 rows