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

Open-ended Hallucination Evaluation on Open-ended hallucination benchmark

1.46Score

REC

0.79440.96721.141.3128Jun 7, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
1.464.22
2026.06
1.444.21
2026.06
1.44.19
2026.06
1.45.32
2026.06
1.385.31
2026.06
1.384.24
2026.06
1.345.33
2026.06
1.325.28
2026.06
1.323.26
2026.06
1.33.25
2026.06
1.283.23
2026.06
1.284.32
2026.06
1.263.28
2026.06
1.264.35
2026.06
1.262.99
2026.06
1.245.2
2026.06
1.242.95
2026.06
1.222.94
2026.06
1.225.4
2026.06
1.224.31
2026.06
1.22.97
2026.06
1.24.38
2026.06
1.183.51
2026.06
1.184.37
2026.06
1.185.16
2026.06
1.165.45
2026.06
1.163.49
2026.06
1.164.4
2026.06
1.145.44
2026.06
1.144.42
2026.06
1.123
2026.06
1.125.46
2026.06
1.13.55
2026.06
1.13.03
2026.06
1.15.48
2026.06
1.082.91
2026.06
1.083.53
2026.06
1.062.91
2026.06
1.063.57
2026.06
1.042.9
2026.06
1.043.05
2026.06
1.043.6
2026.06
1.022.92
2026.06
1.023.04
2026.06
13.06
2026.06
0.982.96
2026.06
0.983.07
2026.06
0.983.45
2026.06
0.962.98
2026.06
0.942.98
2026.06
0.923
2026.06
0.92.99
2026.06
0.883.01
2026.06
0.863.03
2026.06
0.822.88