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

Natural Language Understanding on GLUE (val) - Subset (CoLA, MNLI, MRPC, QNLI, QQP, RTE, SST-2, STS-B)

82.4CoLA Score

ProbSurgery

44.408854.271964.13573.9981Oct 12, 2025Nov 16, 2025Dec 22, 2025Jan 27, 2026Mar 4, 2026Apr 9, 2026May 15, 2026
Updated 15d ago

Evaluation Results

MethodLinks
2026.05
82.469.178.380.689.883.481.292.582.2
2026.05
80.288.589.294.487.291.795.290.989.6
2026.05
79.287.88993.986.988.495.390.888.9
2026.05
77.287.68593.88688.495.287.887.6
2026.05
76.885.485.39485.888.195.287.787.3
2026.05
7687.98693.986.289.995.28988
2026.05
7583.487.591.585.485.993.688.786.4
2026.05
73.756.682.491.185.585.694.387.582.1
2026.05
72.282.685.191.184.785.29387.785.2
2026.05
70.882.482.489.884.28392.185.283.7
2026.05
70.557.878.490.283.680.592.377.878.9
2026.05
69.156.576.288.482.180.191.262.275.7
2026.05
68.290.2787.0794.0789.7381.439691.1387.24
2026.05
67.6390.2787.9394.389.7784.2795.839187.63
2026.05
65.5690.288.2894.3690.0886.196.1491.2887.75
2025.10
58.884.1185.7891.8990.6368.2392.8989.3282.71
2025.10
57.5380.6884.5690.5589.5868.9591.9789.0381.61
2025.10
53.2777.7685.0586.8285.8565.3489.6883.4478.4
2025.10
51.7478.3684.887.3985.8466.7990.3784.2778.69
2026.05
51.6790.288.0393.5790.284.595.791.2585.64
2025.10
49.9272.3785.7885.0183.2266.0688.6583.9276.87
2025.10
49.977.884.887.8185.7162.0990.684.2277.87
2025.10
4881.1678.1987.9488.01---76.66
2025.10
47.781.0982.687.5787.82---77.36
2025.10
47.5973.5283.0985.6784.9863.989.5684.7376.63
2025.10
45.8781.2281.3787.8887.82---76.83