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

Reasoning Quality Assessment on GSM8K

80.61AUROC

TRACED

30.84643.765556.68569.6045Mar 11, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
80.6182.8365
2026.03
79.9682.0468.24
2026.03
79.9581.9570.59
2026.03
78.2577.5857
2026.03
77.7271.7657.54
2026.03
75.5677.1477.5
2026.03
75.172.459.62
2026.03
74.7176.786.43
2026.03
74.2474.2582.35
2026.03
74.176075.1
2026.03
72.9377.478.46
2026.03
70.1173.9277.67
2026.03
69.6671.9983.33
2026.03
69.5668.9580.24
2026.03
68.6369.1682.35
2026.03
68.2968.7786
2026.03
68.168.780.93
2026.03
67.2168.4581.38
2026.03
65.0964.8986.54
2026.03
64.9556.1681.36
2026.03
64.8956.5983.1
2026.03
64.3564.0686.54
2026.03
62.3644.7684.83
2026.03
61.9455.2783.26
2026.03
61.9159.1780.77
2026.03
60.9660.8888.24
2026.03
56.5156.5388.24
2026.03
47.757.1788.21
2026.03
45.7552.7683.42
2026.03
44.8349.5685.46
2026.03
37.7241.2386.55
2026.03
32.7648.3285.34