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

Mathematical Reasoning on AIME 2024 (Avg@5)

94Avg@5 Score

Gemini-3-Pro-Preview

44.0857.047082.96Jan 23, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
94
2026.01
92
2026.01
92
2026.01
90.7
2026.01
90.7
2026.01
90
2026.01
89.3
2026.01
88
2026.01
87.3
2026.01
86.7
2026.01
85.3
2026.01
84.7
2026.01
84
2026.01
82.7
2026.01
81.3
2026.01
79
2026.01
77.7
2026.01
75.3
2026.01
75.3
2026.01
75
2026.01
74.7
2026.01
74
2026.01
73.3
2026.01
73
2026.01
72
2026.01
71.7
2026.01
68.7
2026.01
65.3
2026.01
55.7
2026.01
51.3
2026.01
48.7
2026.01
46