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

Knowledge on TruthfulQA

60.66Score

UM-187k

38.320844.120449.9255.7196Nov 14, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.11
60.66
2025.11
60.57
2025.11
58.23
2025.11
56.28
2025.11
56.21
2025.11
55.87
2025.11
55.62
2025.11
54.71
2025.11
54.21
2025.11
50.38
2025.11
50.24
2025.11
48.1
2025.11
45.73
2025.11
45.5
2025.11
44.43
2025.11
41.19
2025.11
40.94
2025.11
39.18