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

Long-context Language Modeling on LongBench (Aggregated Metrics)

58.4Average Score

Original

40.699245.294649.8954.4854Feb 6, 2025Apr 23, 2025Jul 8, 2025Sep 22, 2025Dec 7, 2025Feb 21, 2026May 8, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.04
58.443.743.52772.166.766.6----------------89.2-----
2026.04
57.145.541.926.870.36366.6----------------85.8-----
2026.04
54.924.639.827.67064.367.8----------------90.1-----
2026.05
54.08------32.2149.5951.8865.2665.5141.373424.3524.747891.7647.8721.599.566.3671.42------
2026.05
53.82------32.6549.5151.6864.7764.9540.4131.7824.2123.947892.0647.9121.599.566.3471.9------
2026.05
53.54------32.550.2451.864.2164.334131.6323.8724.237892.6146.2821.599.565.0369.85------
2026.05
52.72------33.7845.1650.8263.9664.840.8327.4123.0222.2976.591.8945.62299.565.4870.48------
2026.05
52.49------32.545.8151.2364.5664.3940.5526.8923.2422.0775.592.1645.0321.599.565.0469.95------
2026.05
52.3------31.7644.7949.5763.8664.4239.7226.9323.4922.17692.1645.152299.565.4869.8------
2026.05
52.05------31.0343.8950.8164.5964.5839.3526.3323.4221.9273.592.1945.762199.1765.3469.89------
2026.05
51.91------30.646.3850.565.4764.9740.3526.6422.322.147391.8645.2919.59964.0368.52------
2026.04
51.542.636.217.668.855.256.6----------------83.5-----
2026.04
50.646.337.624.765.741.354.8----------------83.4-----
2026.04
50.54638.324.565.44154.9----------------83.5-----
2026.04
49.946.138.724.665.337.552.8----------------84-----
2026.04
49.345.536.225.664.934.558.7----------------79.9-----
2025.02
49.243.146.4928.9769.4553.7357.86---------------------0
2026.05
48.86------30.6833.0749.5463.9262.9338.3521.822.0218.4661.590.9142.1521.599.2559.9465.71------
2025.02
48.5940.4955.3326.3669.2755.0446.54---------------------0
2025.02
48.5843.2354.0327.468.9756.2541.93---------------------0
2025.02
4839.2445.1127.3168.1953.660.6---------------------2.4
2026.04
47.86---------62.0545.1634.6331.5724.7225.3567.587.3540.554.5-63.0459.7-26.7655.339839.59-
2025.02
47.8138.7455.1326.168.3755.0944.88---------------------1.6
2025.02
47.7940.6144.3327.2468.0654.0457.89---------------------2.9
2025.02
47.3838.3739.428.7670.3352.561.25---------------------0
2025.02
47.2938.2743.1727.1566.8754.2260.91---------------------3.9
2026.05
47.25------28.763246.3362.3762.2136.620.9421.3817.95390.2640.812397.4259.0763.89------
47.25------30.1145.454.8555.6446.431.2835.1725.2627.15-91.65---65.1258.97------
2025.02
47.2339.9643.127.0665.6452.8961.34---------------------4
2025.02
47.2337.1854.5526.0367.855.7543.75---------------------2.8
2025.02
47.0335.753.7525.9768.6555.2544.88---------------------3.2
2025.08
46.99------30.0845.0654.7855.3946.1531.234.425.6326.77-91.5---63.7859.21------
2025.08
46.97------29.9945.3554.2755.546.2931.2734.5425.3626.64-91.49---64.0658.88------
2025.08
46.95------30.144.7354.7655.3946.1931.234.3525.3426.72-91.5---63.7259.35------
2025.08
46.9------30.0344.3955.3855.4246.4431.2434.1525.6426.37-91.38---64.1658.23------
2025.08
46.89------30.144.8554.8355.545.9231.233425.4526.9-91.49---63.8558.6------
2025.08
46.86------29.9844.4754.5655.3946.2431.2134.4225.3626.32-91.5---63.9458.98------
2025.08
46.83------30.0744.4355.0655.644631.233.8825.6226.31-91.49---63.6558.63------
2025.08
46.76------29.9144.1254.9755.2245.9231.2233.8125.7126.43-91.49---63.6658.64------
2026.04
46.63---------60.546.3435.1731.2324.925.3248.587.1839.756-61.8855.78-27.2656.139941.1-
2026.04
46.47---------61.5244.0634.231.7724.3625.1151.588.0139.825.5-62.9656.23-26.0155.499838.9-
2026.04
46.41---------58.6443.8435.2130.7524.2424.396187.9340.34-57.2360.79-25.6952.0998.6737.77-
2026.05
46.38------28.0229.5446.362.1761.4737.7320.7221.2717.74790.2840.2221.596.1758.4263.51------
2026.04
46.31---------61.2245.1935.531.0724.7825.1647.587.5240.396-63.0156.76-26.553.489937.86-
2025.08
46.3------30.2942.5454.5354.445.8131.0333.8125.126.26-91.68---62.9757.16------
2025.08
46.26------29.1143.5253.8954.4444.5731.4633.4325.3726.2-91.66---63.6557.87------
2025.08
46.25------29.6843.6753.0854.4244.9330.9533.2925.8326.49-91.68---63.5857.43------
2025.02
46.2436.6341.3626.6666.435360.3---------------------6
2025.02
46.2336.063827.0669.7950.8462.68---------------------2.4
2025.08
46.18------29.7442.9653.454.3344.931.2933.325.5226.54-91.68---63.4757.06------
2025.02
46.136.2137.6627.7269.7850.261.56---------------------2.7
2025.02
46.0332.3752.7524.9568.1854.6346.21---------------------5.3
2026.04
45.67---------59.7543.7334.9131.2523.922562.587.9539.665.5-62.6257.3-27.1850.0382.536.97-
2025.02
45.5235.2740.526.1165.153.1760.49---------------------7.5
2025.02
45.4732.2250.925.1967.4355.2544.89---------------------6.4
2025.02
45.4332.0750.624.3468.5353.8846.27---------------------6.5
2026.04
45.439.830.92667.432.748.2----------------72.6-----
2025.02
45.3534.3336.6126.9468.5751.0562.06---------------------4.3
2025.02
45.0733.4235.9726.2468.6750.7563.35---------------------4.9
2025.02
44.8433.935.2826.7667.4650.563.16---------------------5.4
2026.04
44.48---------58.2841.7432.0929.9223.3223.745.587.5240.164.5-63.8758.54-27.0943.389933.06-
2025.02
44.0331.6433.5726.2467.9549.7563.41---------------------7.1
2025.02
43.9933.636.3325.2865.4152.1858.85---------------------10.6
2025.02
43.7732.7435.3124.9864.7452.361.16---------------------11
2025.02
43.752947.424.0667.4452.7545.43---------------------9.9
2026.04
43.64-------37.38-47.5936.427.233.6324.9926.754.587.1238.325.28-52.4257.85-26.6449.1893--
2026.04
43.46-------38.72-48.437.6826.4634.4925.7426.7452.2585.2830.45.85-51.2957.09-28.450.1196.5--
2025.02
43.4630.9534.4725.6367.5848.0261.76---------------------8.3
2025.02
43.3628.1246.8824.2366.865344.72---------------------10.8
2026.04
43.3-------38.74-46.1239.5726.9533.6725.6126.6455.0586.425.643.73-50.1456.89-27.1252.0198.5--
2025.03
43.244.2344.7228.5225.8853.4462.41----------------------
2025.03
43.244.2344.7228.5225.8853.4462.41----------------------
2026.04
43.18-------40.2-48.9536.8527.7434.5325.3826.8955.7585.0920.525.46-49.7256-28.2951.4998--
2025.02
43.1129.946.3523.8865.9650.8844.83---------------------11.3
2025.02
42.9930.4335.8724.6463.0452.1660.75---------------------12.6
2025.02
42.8731.3934.924.2963.750.3961.14---------------------12.9
2026.04
42.85-------39.23-49.1236.5726.3533.9725.0326.8755.7586.4221.224.09-51.3455.3-26.950.9896.5--
2025.02
42.8529.0633.0424.8367.0849.2562.56---------------------9.6
2025.03
42.8343.1744.1326.0927.7553.2762.56----------------------
2025.03
42.6944.3844.6327.9825.5552.1361.5----------------------
2025.02
42.6431.5334.9724.4962.7949.3261.14---------------------13.3
2025.03
42.6343.1844.428.226.5752.8860.55----------------------
2026.04
42.53-------34.49-45.0536.5225.0332.2224.6925.795288.1135.843.85-46.7559.53-26.0949.5495--
2025.03
42.543.6444.4727.6225.3152.6361.32----------------------
2025.03
42.4742.9243.9925.7327.6253.0261.54----------------------
2025.03
42.444.5845.227.7625.3252.6358.94----------------------
2026.04
42.35-------36.74-47.4337.6826.3533.4524.5826.253.7585.0920.795.66-50.9956.59-26.1348.1398--
2025.03
42.2744.3938.8226.1427.3455.561.44----------------------
2026.04
42.23-------36.98-48.8435.8924.4534.1424.2326.5750.1484.5925.524.77-53.1756.67-26.3748.8294.5--
2026.04
42.22---------47.8437.1526.0831.4623.4525.716083.4736.846.19-50.8348.85-23.6248.099233.88-
2025.03
42.2143.3544.8727.1525.7652.6359.53----------------------
2026.03
42.01----------------------------
2026.04
41.9---------53.3936.5831.5229.223.7422.5352.587.8538.936-46.2561.64-25.342.681.2531.09-
2025.02
41.7827.2531.7124.18664862.55---------------------11.8
2025.02
41.7728.2432.0724.6165.5446.5361.94---------------------11.8
2025.02
41.6127.9431.5824.4964.7347.7961.96---------------------12.2
2025.03
41.5141.7644.8926.0224.7452.7358.91----------------------
2025.03
41.4740.8742.4527.426.9651.759.42----------------------
2026.04
41.42-------32.36-46.5538.9823.1532.0422.9626.0454.7585.439.885.13-54.1757.53-25.142.7676--
2025.02
41.3826.6242.3623.2166.5646.6346.3---------------------14.8
Showing 100 of 328 rows