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

Multiple Choice Question Answering on MMLU-Pro

96.5MMLU-Pro Overall Accuracy

BERT-Judge

33.37249.76166.1582.539Aug 8, 2025Sep 19, 2025Nov 1, 2025Dec 14, 2025Jan 25, 2026Mar 9, 2026Apr 21, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.04
96.5------------------
2026.04
88.8------------------
2026.01
84.8------------------
2025.08
83.7-------------1----
2026.01
82.83------------------
2026.04
82.685.4--85-82.8-85.580.6-70.8---84.283.385.5-
2026.01
82.37------------------
2026.01
81.75------------------
2026.01
80.14------------------
2026.01
80.11------------------
2026.01
79.08------------------
2026.01
78.92------------------
2026.01
78.68------------------
2026.01
78.62------------------
2025.08
78-------------2----
77.9-------------3----
2025.08
77.9-------------4----
2026.04
77.980.8--80.5-79.5-81.376-64.6---79.278.780.7-
2026.04
77.780.3--80.3-79.5-8175.6-64.5---7978.580.5-
2026.04
77.780.8--80.7-78.2-81.375.5-64.7---79.37879.3-
2026.01
76.88------------------
2026.01
75.53------------------
2026.01
74.49------------------
2026.01
74.376.2675.7376.977.3375.7276.7978.7278.2975.7263.4268.6668.12------
2026.01
71.6977.6582.7880.7577.8678.6176.478081.3970.5935.0855.8363.31------
2026.01
70.4874.9779.7980.174.8775.7271.2380.4378.3972.5130.3860.1167.27------
2026.01
69.8370.0578.3978.1876.7976.3663.8578.2977.3374.4446.157.0161.18------
2026.01
69.3175.376.977.3374.1274.2268.5579.7879.3670.736.4755.6163.42------
2026.01
69.373.980.8577.6575.8374.3371.9877.3377.2272.0937.3253.4859.68------
2026.04
69.280.5--79.7-35.7-80.869.3-43.4---77.975.480.1-
2026.01
68.874.6577.6577.5475.7274.8771.3479.5779.2574.1231.4446.163.32------
2026.01
66.8870.2777.2275.9374.1272.9469.8475.8375.8362.0335.454.4458.72------
2026.01
65.474.9879.6875.7275.7275.469.278.8275.366.230.1636.946.74------
2026.01
65.3772.7376.2675.7273.5873.2669.5276.3776.3766.4125.9942.6855.51------
2026.01
63.973.1676.6974.2273.5871.3464.8174.7676.2661.519.8944.1756.47------
2026.01
62.9970.0578.0772.4174.9770.9166.175.5173.0562.0315.5144.0653.16------
2025.08
62.1-------------5----
2026.01
62.0369.4174.4473.6970.3765.9967.5974.1273.0562.1429.9529.4154.23------
2026.01
60.6268.8875.2973.874.0169.267.2773.1573.6961.2814.8629.7346.31------
2026.01
58.2267.4874.7674.4472.1971.6664.8168.7774.3356.0416.5832.1925.35------
2026.01
57.6663.3264.9269.0967.4964.0763.7468.3469.0949.0922.7842.6747.38------
2026.01
57.5860.5372.9469.6269.261.3965.4570.5970.6957.1124.1730.4838.82------
2026.04
57.1------------------
2026.01
56.6869.4174.7673.972.9468.4564.3876.1574.9746.6318.6119.1420.86------
2026.04
56.62------------------
2026.01
56.5769.5275.373.3768.7770.6965.5674.5573.944.9220.6424.4917.11------
2026.04
56.57------------------
2026.01
56.253.1575.9473.5871.9851.8760.3271.6672.8357.6524.0627.1734.23------
2026.01
55.08------------------
2026.01
54.7862.4667.3868.9864.4958.557.9770.2767.754.5413.1527.5944.28------
2026.01
54.7166.3175.2972.8471.5570.6966.3171.0271.3444.9212.7317.4316.04------
2026.04
54.65------------------
2026.01
54.25------------------
2026.01
53.79------------------
2026.01
53.557.1171.9868.1365.8860.4356.6866.6368.3448.0216.4727.8134.54------
2026.01
53.4769.9573.869.7368.2466.8461.671.5569.335.5118.1815.421.5------
2026.01
53.14------------------
2026.01
53.1259.8972.366.6367.8159.8952.366.6368.6650.820.7522.9928.77------
2026.01
52.87------------------
2026.01
52.66------------------
2026.01
51.95------------------
2026.01
51.8259.3668.4571.6663.159.8955.6168.4572.6236.3615.5120.9629.84------
2026.01
51.29------------------
2026.01
51.24------------------
2025.11
50.82------------------
2025.11
50.77------------------
2026.01
50.5669.5275.469.4167.9163.8556.0467.9167.5918.6116.3618.2915.83------
2026.01
50.1556.5872.7365.5665.9954.8747.4966.5268.3437.2214.6521.2830.59------
2026.01
49.7962.4672.368.8766.5264.9262.5768.1368.1324.0612.9413.5813.05------
2026.01
48.5465.1371.3465.2465.9958.457.2268.7765.6724.3811.3412.8316.15------
2026.01
48.4651.6672.5165.5668.0256.6848.8868.0266.3133.5813.5818.6118.08------
2026.01
48.3------------------
47.15------------------
2025.11
47.07------------------
2026.01
47.0251.1261.558.7158.3953.0551.8759.0458.6145.999.4123.6332.94------
2025.11
47------------------
2026.01
46.0456.7970.0565.2464.9258.9348.9865.1365.7823.6411.3410.4811.23------
2026.01
45.0547.5965.7858.2960.3252.8340.4356.4759.6839.1412.5120.7526.84------
2026.01
44.7661.3968.2358.461.9354.8756.963.7459.6819.5710.9110.9110.59------
2026.01
44.7359.5768.1357.9757.7552.5149.260.8659.8920.4316.914.1219.47------
2026.01
44.2758.1863.7564.3960.7557.4353.5861.561.615.312.0812.849.84------
2025.08
42.3-------------6----
2026.01
41.9758.566.9554.6554.7652.345.6756.4757.8619.6811.6613.0512.09------
2026.04
41.65------------------
2026.01
39.3853.858.2957.4353.1648.7741.3959.3658.6110.3711.349.5210.48------
2025.11
37.95------------------
2026.02
37.5------------------
2026.02
37.2------------------
2026.02
36.9------------------
2026.04
36.86------------------
2026.02
36.8------------------
2026.02
36.7------------------
2026.02
36.7------------------
2026.01
36.653.1659.1550.850.5943.6437.7548.3450.2712.5111.2311.0210.7------
2026.02
36.6------------------
2026.02
36.4------------------
2026.01
36.3247.0654.3351.6649.5241.1835.6148.6645.2428.8811.6611.7610.27------
2026.02
36.1------------------
2026.02
35.9------------------
2026.02
35.8------------------
Showing 100 of 130 rows