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

Textual Reasoning on Averaged

85.63TPS

STDec

4.655625.677846.767.7222Apr 7, 2026
Updated 9d ago

Evaluation Results

MethodLinks
2026.04
85.6310.0355.16
2026.04
67.937.9554.44
2026.04
59.097.646.87
2026.04
53.676.9146.17
2026.04
50.035.8655.79
2026.04
42.995.5346.95
2026.04
17.08243.42
2026.04
15.55243.25
2026.04
12.991.5252.43
2026.04
12.061.5547.36
2026.04
8.54154.3
2026.04
7.77146.59