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

Mathematical Reasoning on MATH500 (Acc, RL, SL, RE, SE)

89.2Accuracy

L1

81.368883.401985.43587.4681Mar 23, 2026
Updated 2mo ago

Evaluation Results

MethodLinks
2026.03
89.22,1332,6034.183.43
2026.03
89.23,7614,2972.372.08
2026.03
88.332,9544,5542.991.94
2026.03
87.52,6523,0633.32.86
2026.03
87.52,4222,8073.613.12
2026.03
851,8672,5634.553.32
2026.03
82.55391,42615.315.79
2026.03
81.671,0421,8737.844.36