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

Mathematical Reasoning on GSM8K (Acc, TPF, AUP)

96Accuracy

Orthrus-Qwen3-8B

38.38453.34268.383.258Mar 4, 2026Mar 18, 2026Apr 2, 2026Apr 17, 2026May 2, 2026May 17, 2026Jun 1, 2026
Updated 22h ago

Evaluation Results

MethodLinks
2026.05
96--
2026.05
94.9--
2026.05
94.4--
2026.05
93.2--
2026.05
93--
2026.05
92.8--
2026.05
92.57--
2026.06
92.5--
2026.05
92.4--
2026.06
92.3--
2026.05
91.74--
2026.05
91.7--
2026.05
91.4--
2026.05
90.8--
2026.06
90.4--
2026.03
90.35.58492.4
2026.05
90.22--
2026.05
89.99--
2026.05
89.84--
2026.06
89.3--
2026.06
89.2--
2026.04
89.1--
2026.05
89--
2026.03
88.92.85252.5
2026.05
88.63--
2026.05
88.5--
2026.05
87.65--
2026.06
87.6--
2026.05
87.33--
2026.04
87.2--
2026.04
87--
2026.05
86.8--
2026.04
86.7--
2026.05
86.4--
2026.05
86--
2026.06
86--
2026.06
85.7--
2026.05
85.6--
2026.04
85.4--
2026.06
85.4--
2026.05
85.2--
2026.05
85--
2026.05
84.8--
2026.05
84.2--
2026.03
83.9183.9
2026.06
83.9--
2026.05
83.7--
2026.05
82.4--
2026.03
82.13.02245.7
2026.03
81.44.94391.3
2026.06
81.2--
2026.05
81--
2026.04
80.9--
2026.05
79.3--
2026.06
79.3--
2026.03
791.44116.5
2026.03
77.52.21156
2026.06
77.3--
2026.06
77.3--
2026.03
76.65.12319
2026.04
76--
2026.05
75.2--
2026.03
74.72.77205.8
2026.03
74.1174.1
2026.05
73.8--
2026.03
73.22.88209.7
2026.03
73.19.11637.7
2026.03
72.6172.6
2026.03
72.65.14358.1
2026.05
72.4--
2026.06
71.8--
2026.06
71.3--
2026.06
69.8--
2026.06
65.4--
2026.05
63--
2026.05
48.5--
2026.05
48.2--
2026.05
46.5--
2026.05
46.3--
2026.05
46--
2026.05
45.7--
2026.05
45.2--
2026.05
45.1--
2026.05
45.1--
2026.05
44.9--
2026.05
44.9--
2026.05
44.6--
2026.05
44.6--
2026.05
44.4--
2026.05
44--
2026.05
43.8--
2026.05
42.7--
2026.05
42.4--
2026.05
41.4--
2026.05
40.6--