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

Reasoning on GSM8K, MATH-500, AIME24, AIME25, GPQA-D

95.15GSM8K Accuracy

BF16

91.998892.816993.63594.4531Mar 17, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
95.1596.8771.4663.1258.1376.95100
2026.03
94.9296.2765.6256.0454.873.5394.8
2026.03
94.8496.468.3359.3857.2275.2397.46
2026.03
94.7795.662.0852.9254.1971.9192.45
2026.03
94.7795.2766.0454.4854.2472.9694
2026.03
94.6995.5360.4251.4654.5871.3491.62
2026.03
94.6995.3360.7147.2952.4270.0989.6
2026.03
94.6995.3363.7552.7154.0472.192.72
2026.03
94.6295.9369.1757.0854.874.3295.99
2026.03
94.6296.2769.3755.2156.8274.4696.22
2026.03
94.549665.4253.9654.5572.8993.87
2026.03
94.4795.6764.1755.6354.3972.8793.91
2026.03
94.4795.4759.3853.9655.8671.8792.56
2026.03
94.4796.136557.0853.9473.3294.54
2026.03
94.3996.3368.0259.3855.174.6496.54
2026.03
94.3996.1366.0454.7954.2973.1394.21
2026.03
94.2495.7357.552.0852.1270.3390.1
2026.03
94.0992.4747.539.3748.1364.3181.2
2026.03
94.0995.7364.7955.8354.4972.9994.11
2026.03
94.0995.463.3353.5454.9572.2693.07
2026.03
94.0194.862.0852.551.8271.0491.17
2026.03
93.789560.2154.7953.5471.4691.96
2026.03
93.7195.5364.585554.3972.6493.64
2026.03
93.7195.863.9653.3355.472.3993.26
2026.03
93.5695.1362.0849.1753.5470.790.68
2026.03
93.491.6738.5735.6345.6660.9976.35
2026.03
93.494.3358.9643.5450.5168.1586.78
2026.03
93.493.0747.9239.5849.7564.7481.92
2026.03
93.2594.3357.7149.5852.1269.488.87
2026.03
93.194.5353.3347.0849.867.5786.06
2026.03
93.0392.7346.6740.3349.1963.3981.46
2026.03
92.2791.7337.2934.5848.0360.7876.25
2026.03
92.1291.1343.5438.7546.9762.578.8