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

Single-turn Reasoning on AIME24, AIME25, and GPQA

92.2AIME 2024 Accuracy

SKillOS

72.54477.64782.7587.853May 7, 2026
Updated 26d ago

Evaluation Results

MethodLinks
2026.05
92.286.786.888.6
2026.05
9085.680.785.4
2026.05
87.883.382.884.6
2026.05
85.681.172.479.7
2026.05
85.68079.981.8
2026.05
85.684.480.483.5
2026.05
83.376.781.880.6
2026.05
82.276.766.575.1
2026.05
81.472.268.474
2026.05
81.175.666.974.9
2026.05
8076.764.673.8
2026.05
8075.667.774.7
2026.05
77.874.466.273.2
2026.05
7671.161.869.6
2026.05
75.671.160.669.1
2026.05
75.671.959.368.9
2026.05
75.473.260.369.6
2026.05
73.371.357.667.4