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

Open-ended Generation on TruthfulQA

70.13BLEURT Score

FineSteer

50.338855.476960.61565.7531Apr 16, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.04
70.1370.9
2026.04
68.7466.01
2026.04
66.562.35
2026.04
66.562.35
2026.04
65.3154.79
2026.04
64.5361.86
2026.04
64.1562.59
2026.04
63.7961.37
2026.04
63.5754.28
2026.04
63.5754.28
2026.04
62.7760.23
2026.04
62.7350.61
62.3458.92
2026.04
62.149.88
2026.04
62.149.88
2026.04
61.6654.77
2026.04
61.6654.77
2026.04
61.5359.9
2026.04
60.1747.92
2026.04
60.1747.92
2026.04
59.6648.17
2026.04
59.6648.17
2026.04
59.4148.41
59.4148.41
2026.04
58.6848.66
2026.04
58.6848.66
2026.04
58.4447.92
2026.04
58.4447.92
2026.04
57.2147.43
2026.04
57.2150.37
2026.04
57.2147.43
2026.04
56.7247.19
2026.04
55.7447.95
2026.04
54.9250.32
2026.04
54.9250.32
2026.04
54.2842.05
2026.04
53.6645.97
2026.04
53.4251.83
2026.04
53.4251.83
52.0941.08
2026.04
51.9848.9
2026.04
51.9848.9
2026.04
51.3447.43
2026.04
51.3447.43
2026.04
51.2350.37
2026.04
51.2350.37
2026.04
51.145.48
51.145.48