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

Factual Knowledge Evaluation on HHEM, PopQA, TriviaQA Suite

96.22HHEM Accuracy

SEAL

83.615286.887690.1693.4324Apr 2, 2026
Updated 16d ago

Evaluation Results

MethodLinks
2026.04
96.2258.5470.3575.04
2026.04
95.1360.8371.2275.73
2026.04
95.0359.5468.974.49
2026.04
94.8358.8969.3474.35
2026.04
94.8354.969.2272.98
2026.04
94.8359.1170.7274.89
2026.04
94.5358.5468.9574.01
2026.04
92.2557.7668.8772.96
2026.04
89.7659.7569.2372.91
2026.04
88.5757.7667.9471.42
2026.04
88.1258.1868.171.47
2026.04
84.150.8966.4767.15