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

Zero-shot Evaluation Suite (ARC, Hellaswag, LAMBADA, PIQA, Winogrande)

73.39ARC-C

FP16

26.79838.89450.9963.086May 11, 2026
Updated 14d ago

Evaluation Results

MethodLinks
2026.05
73.3987.4287.8984.6287.3284.7684.23
2026.05
73.3987.4287.8984.6287.3284.7684.23
2026.05
67.4185.9785.2180.1785.6281.4980.97
2026.05
65.9884.8784.0878.3284.8780.3979.75
2026.05
64.5182.6383.4279.4483.7675.6378.23
2026.05
64.5182.6383.4279.4483.7675.6378.23
2026.05
64.2585.9484.9379.3784.4480.7479.95
2026.05
64.2585.9484.9379.3784.4480.7479.95
2026.05
64.2585.9484.9379.3784.4480.7479.95
2026.05
64.2585.9484.9379.3784.4480.7479.95
2026.05
64.2585.9484.9379.3784.4480.7479.95
2026.05
63.7681.0381.2775.8681.3677.276.74
2026.05
62.8384.8884.0779.4284.0179.5679.13
2026.05
62.8384.8884.0779.4284.0179.5679.19
2026.05
61.9584.4783.8777.9983.9579.2478.58
2026.05
61.9584.4783.8777.9983.9579.2478.58
2026.05
61.0878.6478.3273.6279.6274.4274.28
2026.05
59.7678.8177.8976.6379.6473.9874.45
2026.05
58.6476.8876.4975.3179.3873.4273.35
2026.05
57.7181.0283.8179.682.777.9877.05
2026.05
57.3874.275.5574.3678.8370.7671.84
2026.05
56.680.3282.9779.8482.977.0376.61
2026.05
56.480.0982.9180.0182.9276.8776.53
2026.05
56.1281.2279.6374.7980.1475.6774.59
2026.05
55.6773.6472.9771.9376.3768.1869.79
2026.05
55.4679.7681.5879.3581.8376.0975.68
2026.05
55.3879.0482.5778.7582.3778.2276.06
2026.05
54.7682.0776.6473.5268.9368.9270.81
2026.05
54.3780.3178.6773.5779.0373.3773.22
2026.05
53.577.5779.1275.5180.7472.9373.23
2026.05
53.577.5779.1275.5180.7472.9373.23
2026.05
53.577.5779.1275.5180.7472.9373.23
2026.05
53.577.5779.1275.5180.7472.9373.23
2026.05
53.577.5779.1275.5180.7472.9373.23
2026.05
53.2680.0677.4972.5778.3971.5372.22
2026.05
53.2680.0677.4972.5778.3971.5372.22
2026.05
52.7880.1274.0371.7766.7366.7468.69
2026.05
52.2878.2476.6172.1877.3770.7871.24
2026.05
51.9677.477.2971.979.3372.0671.66
2026.05
51.9677.477.2971.979.3372.0671.66
2026.05
51.0376.176.7773.4278.5772.8871.46
2026.05
51.0376.176.7773.4278.5772.8871.46
2026.05
50.7178.6175.8270.9375.4268.6870.02
2026.05
50.7178.6175.8270.9375.4268.6870.02
2026.05
50.5175.8876.4973.27972.9371.33
2026.05
50.5175.8876.4973.27972.9371.33
2026.05
50.3778.0972.4669.164.5264.5766.51
2026.05
49.4974.3777.2271.6978.8971.0370.45
2026.05
49.4974.3777.2271.6978.8971.0370.45
2026.05
49.1577.4479.3976.7380.4772.1472.55
2026.05
48.7476.7463.0167.7973.8265.9366.01
2026.05
48.7476.7463.0167.7973.8265.9366.01
2026.05
48.5276.8777.976.4779.8370.7771.73
2026.05
48.3876.9477.8876.479.6570.5671.64
2026.05
47.8674.3170.5367.5772.0967.5366.64
2026.05
47.2774.274.5570.2977.3768.5168.7
2026.05
47.2774.274.5570.2977.3768.5168.7
2026.05
46.3774.370.0564.0762.0761.8763.12
2026.05
46.1674.5475.9873.9279.0569.0669.79
2026.05
45.7370.8372.9762.775.3567.1765.79
2026.05
45.7370.8372.9762.775.3567.1765.79
2026.05
43.6972.4375.5272.4278.468.968.56
2026.05
43.4366.8365.6157.9872.6262.3861.47
2026.05
43.0773.0973.3672.0677.5767.967.84
2026.05
4371.2173.3172.0677.5367.7267.47
2026.05
42.8369.9573.5465.6277.6967.8866.25
2026.05
42.7672.0768.6262.5768.9459.7662.45
2026.05
42.7672.0768.6262.5768.9459.7662.45
2026.05
42.3268.3572.5365.476.3365.1165.01
2026.05
41.7269.2872.971.2876.1766.0666.23
2026.05
40.7664.6462.3453.1669.3559.1558.23
2026.05
38.7762.7259.8751.3367.7357.4256.31
2026.05
37.465.365.353.673.8961.4259.48
2026.05
36.6964.8964.3952.8872.7160.3358.65
2026.05
36.6964.8964.3952.8872.7160.3358.65
2026.05
35.4163.2665.352.4973.5660.6958.45
2026.05
34.7858.7557.4646.8764.3154.3852.75
2026.05
33.3761.2662.5549.0768.5956.8955.28
2026.05
33.3761.2662.5549.0768.5956.8955.28
2026.05
32.5561.0363.5949.871.2957.9356.03
2026.05
31.7758.9361.2947.3666.2555.4253.5
2026.05
31.7758.9361.2947.3666.2555.4253.5
2026.05
28.9357.4260.3345.8166.3454.2552.18
2026.05
28.5954.7654.6241.960.0351.3348.53
2026.05
28.5954.7654.6241.960.0351.3348.53