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

Text-to-action generation on OpenExp-Action-100

16.33Validity Score (Val)

GPT-5

-0.314.018.3312.65Apr 18, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.04
16.3351.5537.4352.337151.6265.47
2026.04
14.6758.7244.236071.7154.2466.51
2026.04
13.3350.6136.56-70.7351.3165.06
2026.04
12.6758.2643.9959.6771.2854.2166.49
2026.04
10.6758.9943.0161.3371.6252.7965.85
2026.04
10.3358.2842.3756.6771.1352.3165.65
2026.04
8.6738.3226.212259.1242.3253.56
2026.04
1.3550.3939.3950.1766.3152.5362.76
2026.04
0.3351.7837.2337.3362.9246.2558.9