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

Mathematical Reasoning on Beyond-AIME v1 (test)

76.6Avg@5

Gemini-3-Pro-Preview

26.88839.79452.765.606Jan 23, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
76.6
2026.01
74
2026.01
73
2026.01
71.8
2026.01
71.6
2026.01
69.8
2026.01
69.4
2026.01
68.2
2026.01
68
2026.01
67.6
2026.01
66.4
2026.01
66
2026.01
58.8
2026.01
58.8
2026.01
58.2
2026.01
57.2
2026.01
57
2026.01
56.8
2026.01
55.8
2026.01
54.8
2026.01
54.8
2026.01
54.4
2026.01
54.4
2026.01
53.6
2026.01
53.6
2026.01
53
2026.01
51.6
2026.01
44
2026.01
37
2026.01
34.6
2026.01
30.6
2026.01
28.8