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

Multilingual Reasoning on MT-AIME 24

44.4Accuracy (%)

ROSA2

0.51211.90623.334.694Sep 27, 2025Oct 23, 2025Nov 18, 2025Dec 14, 2025Jan 9, 2026Feb 4, 2026Mar 2, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
44.4
2025.09
43.93
2025.09
42.27
2025.09
40.16
2026.03
40
2026.03
38.6
2026.03
37.8
2026.03
37.6
2026.03
37
2025.09
30.37
2025.09
30.21
2026.03
29.4
2025.09
27.14
2025.09
26.75
2026.03
21.4
2025.09
19.24
2026.03
17.2
2026.03
17
2026.03
16.2
2026.03
9.6
2025.09
9.43
2025.09
8.19
2025.09
7.9
2025.09
7.58
2025.09
7.27
2026.03
7.2
2026.03
7
2025.09
6.13
2025.09
6.13
2025.09
4.9
2025.09
4.8
2026.03
4.8
2025.09
4.73
2026.03
4.4
2026.03
3.8
2025.09
3.67
2025.09
3.48
2026.03
3.2
2026.03
2.6
2026.03
2.2