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

Hallucination Robustness on HallusionBench

57.8Score

PolarMem

39.80844.47949.1553.821Jan 31, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
57.8
2026.01
56.3
2026.01
55.1
2026.01
54.9
2026.01
54.9
2026.01
54.7
2026.01
53.8
2026.01
53.5
2026.01
52.9
2026.01
52.7
2026.01
52.7
2026.01
52
2026.01
51.5
2026.01
50.3
2026.01
49.6
2026.01
49
2026.01
48
2026.01
48
2026.01
46.9
2026.01
46.2
2026.01
45.4
2026.01
45.2
2026.01
45.1
2026.01
44.8
2026.01
44.8
2026.01
44.7
2026.01
44
2026.01
43.4
2026.01
43.4
2026.01
42.8
2026.01
42.8
2026.01
40.5