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

LLM-as-a-Judge on SenseBench

86.53Math Score

SenseJudge

52.00260.96669.9378.894Jun 2, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
86.5387.9683.6992.2475.2781.0478.7275.7882.65
2026.06
84.5879.3471.882.3973.4369.875.6972.4474.98
2026.06
82.389.0179.7689.8779.8282.1278.175.2381.99
2026.06
73.4580.972.4485.6772.8975.2476.874.2176.88
2026.06
72.862.2766.6777.0762.6764.464.861.8766.57
2026.06
71.7364.869.27861.4767.666.2756.1366.9
2026.06
70.461.666.174.1646062.758.464.7
2026.06
69.658.9363.4754.1352.5350.456.5359.7358.17
2026.06
67.263.264.869.076054.1358.459.7362.07
2026.06
6661.665.4772.9360.863.265.4756.463.98
2026.06
6659.661.267.255.4758.1360.459.3360.92
2026.06
64.452.6755.7353.8739.3342.44836.449.1
2026.06
63.8761.4761.8776.2760.1366.464.457.0763.93
2026.06
63.7363.8763.7369.8759.6759.4757.3355.4761.35
2026.06
62.1358.859.737258.1358.5360.1353.660.33
2026.06
60.2760.859.3370.1361.66264.457.261.97
2026.06
53.3355.661.3353.4746.9350.5351.7350.6752.95