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

Hallucination Robustness on Hallusion-Bench

65.35aAcc

SceneAlign

25.268435.674246.0856.4858Jan 9, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
65.3541.0541.78
2026.01
62.8837.5738.02
2026.01
62.139.4539.2
2026.01
61.7236.8835.01
2026.01
60.3436.7235.84
2026.01
58.2534.5933.64
2026.01
57.8432.9631.42
2026.01
57.6534.2834.2
2026.01
57.3133.2432.09
2026.01
53.2828.1528.36
2026.01
49.5826.0324.45
2026.01
46.8924.5718.02
2026.01
41.8520.8112.53
2026.01
41.6420.2314.95
2026.01
39.3520.0214.74
2026.01
34.2817.0520.66
2026.01
26.8118.7912.75