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

Generative Hallucination on Object HalBench

61CHAIR_S Score

LCD

-1.9214.41530.7547.085Mar 1, 2025May 15, 2025Jul 30, 2025Oct 14, 2025Dec 28, 2025Mar 14, 2026May 29, 2026
Updated 2d ago

Evaluation Results

MethodLinks
2025.03
6116.1
2025.03
48.124.4
2025.03
47.413.9
2025.03
45.122.3
2025.03
40.317.8
2025.03
39.919.9
2026.05
28.312.1
2026.05
2710.5
2026.05
2711.3
2026.05
26.39.2
2026.05
26.310.6
2025.05
26.149.7
2025.03
259.2
2026.05
24.17.8
2025.03
23.68.4
2025.03
23.27.3
2025.05
23.242.3
2026.05
238.3
2026.05
22.37.4
2025.03
22.17.8
2025.05
21.244.3
2025.03
20.86.6
2026.05
20.37.3
2025.05
19.939.9
2026.05
19.76.5
2025.05
19.438.3
2025.03
17.410.7
2025.03
16.66.8
2025.05
16.633.3
2025.05
1630.7
2025.03
15.28
2025.05
14.624.3
2025.03
13.67.3
2025.05
11.724.3
2025.05
5.47.3
2025.05
4.26.3
2025.05
4.26
2025.05
3.65.3
2025.03
0.97.6
2025.03
0.88.9
2025.03
0.79.1
2025.03
0.78.3
2025.03
0.56.8