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

Fact-checking on ExpertQA

61.1Balanced Accuracy

ANCHOR

49.34852.39955.4558.501Feb 23, 2025May 7, 2025Jul 20, 2025Oct 2, 2025Dec 14, 2025Feb 26, 2026May 11, 2026
Updated 22d ago

Evaluation Results

MethodLinks
2026.05
61.1-
2025.02
60.3-
2025.02
59.6-
2025.02
59.3-
2026.05
59-
2025.02
58.8-
2025.02
58.8-
2025.02
58.5-
2025.02
58.3-
2026.05
58.2-
2025.02
57.5-
2025.02
57.4-
2025.02
57.2-
2026.05
56.2-
2025.02
56-
2026.05
55.2-
54.3-
54.1-
2026.05
54.1-
2026.05
53.8-
2025.02
53.6-
2026.05
53-
2026.05
51.7-
2025.02
51.3-
2026.05
49.8-
2026.01
-49.8
2026.01
-55.6
2026.01
-74.4
2026.01
-74.4
2026.01
-68.3
2026.01
-80.3
2026.01
-75.9
2026.01
-79.6
2026.01
-72.7
2026.01
-75
2026.01
-75.3
2026.01
-72.9
2026.01
-78.3
2026.01
-75.7