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

Mathematical Reasoning on OlyBench

44.7Accuracy

ES + TT-MV

2.5813.51524.4535.385Feb 18, 2025Apr 23, 2025Jun 27, 2025Aug 30, 2025Nov 3, 2025Jan 6, 2026Mar 12, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
44.7
2025.02
44.6
2026.03
43.3
2025.02
41.8
2025.02
40.4
2026.03
39.7
2026.03
39.2
2025.02
38.2
2026.03
36.4
2025.02
36.2
2026.03
35.4
2026.03
34.4
2026.03
33.1
2025.02
32.2
2026.03
32.1
2026.03
32.1
2026.03
30.5
2026.03
30.4
2025.02
30.3
2026.03
30.2
2026.03
29
2026.03
28.9
2026.03
28.9
2026.03
28.7
2026.03
28
2026.03
28
2026.03
27.9
2026.03
27.2
2026.03
26.5
2026.03
26.3
2026.03
24.5
2026.03
24.5
2026.03
23.7
2026.03
23
2026.03
22.9
2025.02
22.8
2026.03
22.3
2026.03
21.8
2026.03
20.5
2026.03
20
2026.03
19.2
2026.03
18.8
2026.03
16.4
2026.03
16.1
2026.03
16.1
2026.03
15.9
2026.03
15.8
2026.03
15.7
2025.02
15.6
2025.02
14.6
2026.03
13.9
2026.03
13.5
2026.03
13.4
2026.03
10.5
2025.02
9.9
2026.03
6.9
2026.03
6.9
2026.03
6.7
2026.03
4.2