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

Hallucination Evaluation on Style-CHAIR

19.4Average CI Score

Fuyu

2.767.0811.415.72Aug 5, 2025
Updated 18d ago

Evaluation Results

MethodLinks
2025.08
19.420.669.319.169.72559.316.958.719.753.714.959.361.7
2025.08
10.6------------33.9
2025.08
10.3------------35.3
2025.08
10.1------------35.2
2025.08
9.7------------30
2025.08
9.4------------23.9
2025.08
9.111.4279.120.310.521921.79.423.35.41421.2
2025.08
8.8------------20
2025.08
8.3------------27.3
2025.08
8.1------------27.3
2025.08
78.4156.4139.514.77.1127.414.33.16.312.6
2025.08
6.99.119.37.2148.2166.9137.113.72.65.713.6
2025.08
6.68.116.75.410.38.917.36.613.36.212.34.38.713.1
2025.08
6.37.9145.911813.76.811.76.3123.15.311.3
2025.08
6.39.7146.89.76.69.75.89.7692.759.5
2025.08
5.36.112.35.611.75.812.35.211.36.6142.55.311.2
2025.08
4.75.68.35.68.36.284.764.36.31.62.76.6
2025.08
4.25.810.3595.28.3354.36.7247.2
2025.08
46.58.73.24.34.15.34.86.74.461.21.75.5
2025.08
3.84.9634.32.32.76.993.44.72.33.75.1
2025.08
3.46.273.13.72.42.74.363.650.70.54.2