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

Zero-shot Language Understanding on Qwen3-0.6B Evaluation Suite (test)

68.64Accuracy (AE)

AMO

63.523264.851666.1867.5084May 18, 2026
Updated 15d ago

Evaluation Results

MethodLinks
2026.05
68.6431.9786.826.046.2339.0525.469.733.7854.9620.3117.640.04
2026.05
68.5631.7488.2257.9939.12670.1834.4554.5620.2317.6840.31
2026.05
68.3930.2986.625.067.7739.1826.470.3833.8854.9621.6417.1940.15
2026.05
68.3232.0887256.18392570.843354.2219.7416.4639.74
2026.05
68.3318724.635.5439.112672.0933.785520.7217.7440.08
2026.05
67.4731.487.126.516.9939.1424.469.5932.7354.0620.1517.8639.78
2026.05
66.8831.7486.826.217.2539.072570.3533.5953.6721.6217.7139.99
2026.05
66.5129.6186257.2138.632270.2433.8852.5619.7716.4338.99
2026.05
66.531.5786.626.27.7739.122570.0833.454.2221.717.9440.01
2026.05
66328825.67.9939.125.670.53453.4321.2918.340.15
2026.05
65.5331.238624.555.7237.7423.470.0233.6853.9921.0517.7239.22
2026.05
65.3229.6186.424.636.4637.9423.668.6632.5453.4319.9817.9638.88
2026.05
65.1731.238624.897.837.94246831.5354.0619.7717.7239.01
2026.05
64.9428.418724.26.5937.0523.268.533.1155.0120.7217.638.86
2026.05
63.7229.2786.224.797.0136.5224.268.9933.454.6222.4418.0739.1