Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Long-context evaluation on RULER 16k

95.02Total Score

Full-KV

6.474429.462252.4575.4378Feb 3, 2026Feb 4, 2026Feb 5, 2026Feb 6, 2026Feb 7, 2026Feb 8, 2026Feb 9, 2026
Updated 2d ago

Evaluation Results

MethodLinks
2026.02
95.0210010010010099.810099.9599.8510097.796.279.462.4
2026.02
94.110010010099.499.696.696.789.897.260.895.5--
2026.02
93.610099.892.699.699.29397.394.995.474.580.4--
2026.02
9310010010098.610096.499.299.494.437.197.4--
2026.02
91.610010099.897.699.896.697.494.799.123.798.5--
2026.02
90.610099.89998.210099.692.291.390.340.286.4--
2026.02
88.8810010010010086.646.899.9599.2510096.0296.271.659
2026.02
88.57-------------
2026.02
86.6394.296.499.697.495.676.888.6589.596.2882.2287.9371.650
2026.02
80.8110010010099.844.22399.99999.8895.3499.074446.4
2026.02
80.4799.899.23284.271.878.485.884.699.7295.6693.136556.8
2026.02
79.6685.676.61008790.835.292.8596.4592.1680.7886.864.646.8
2026.02
74.981001001001008199.9599.498.9290.3699.3336.441.4
2026.02
73.4-------------
2026.02
72.795.294.870.893.286.469.483.257.866.713.369.2--
2026.02
72.69-------------
2026.02
70.9-------------
2026.02
70.6810010099.899.610.299.9599.5584.5269.2698.9330.235.8
2026.02
69.9870.878.818.283.679.267.476.2567.895.8878.3284.476247
2026.02
67.5192.691.297.487.86.81.286.458891.2875.4486.4736.436.6
2026.02
66.82-------------
2026.02
65.794.672.810078.87.40.886.194.894.1665.5690.8732.435.8
2026.02
65.5793.296.299.688.26.60.689.759294.3636.9288.7331.434.8
2026.02
59.57-------------
2026.02
59.1-------------
2026.02
56.64-------------
2026.02
56.02-------------
2026.02
54.71-------------
2026.02
54.67-------------
2026.02
53.91-------------
2026.02
52.29-------------
2026.02
50.1-------------
2026.02
48.96-------------
2026.02
48.59-------------
2026.02
48.31-------------
2026.02
44.0498.852.64.421.874.218.2514.7599.3288.4894.5329.439
2026.02
43.9197.455.63.825.84.8219.614.499.2887.14942839
2026.02
41.64-------------
2026.02
38.27-------------
2026.02
37.485838.82.420.212.45.616.812.8592.0871.3686.1333.637
2026.02
36.8383.8362.419.22014.9513.1593.6856.8495.7326.434.6
2026.02
35.12-------------
2026.02
32.4350572.4284.80.221.5516.1562.3231.9482.23233
2026.02
32.18-------------
2026.02
30.75-------------
2026.02
30.44-------------
2026.02
29.5340.416.22.414.26.21119.6566.9266.9685.5329.833.6
2026.02
25.76-------------
2026.02
24.82-------------
2026.02
24.39-------------
2026.02
24.29-------------
2026.02
24.21-------------
2026.02
20.94-------------
2026.02
15.86-------------
2026.02
15.79-------------
2026.02
12.84-------------
2026.02
12.44-------------
2026.02
10.94-------------
2026.02
9.88-------------