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

Mathematical Reasoning on Minerva (Acc, Cost)

50.4Accuracy (Acc)

DYPO

-0.081613.024226.1339.2358Oct 30, 2025Nov 26, 2025Dec 24, 2025Jan 21, 2026Feb 18, 2026Mar 18, 2026Apr 15, 2026
Updated 3d ago

Evaluation Results

MethodLinks
2026.04
50.4-
2026.04
46.3-
2025.10
45.6-
2026.04
44.9-
2025.10
44.9-
2025.10
44.1-
2026.04
43-
2026.03
41.9-
2026.03
41.9-
2026.03
41.5-
2026.03
41.2-
2025.10
40.3-
2025.10
39-
2026.03
38.6-
2026.03
38.6-
2026.03
38.2-
2025.10
37.9-
2025.10
37.5-
2025.10
37.1-
2025.10
37.1-
2026.03
36.4-
2025.10
34.6-
2025.10
33.1-
2026.03
31.43,801
2026.04
31.3-
2026.04
30.5-
2026.04
30.2-
2026.04
29.7-
2026.04
29.4-
2026.04
29-
2026.04
28.6-
2026.04
27.9-
2026.03
26.83,320
2026.04
26.1-
2026.03
25.953,416
2026.04
25.9-
2026.04
25.5-
2025.10
25-
2026.04
24.9-
2026.04
24.9-
2026.04
24.9-
2026.04
24.7-
2026.04
24.63-
2026.04
23.8-
2026.04
22.9-
2026.04
21.69-
2026.04
21.32-
2026.04
20.96-
2026.04
20.96-
2026.04
20.96-
2026.04
19.49-
2026.03
12.1-
2025.10
7.4-
2026.03
4.61,394
2026.03
4.381,776
2026.03
4.261,700
2026.03
3.137,222
2026.03
3.085,808
2026.03
2.686,530
2026.03
2.174,540
2026.03
1.884,839
2026.03
1.865,370