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

Mathematics on AIME 2024 (Accuracy)

65.56Accuracy

Qwen3.5-9B

-1.915215.602433.1250.6376Apr 21, 2025Jun 27, 2025Sep 3, 2025Nov 10, 2025Jan 16, 2026Mar 25, 2026Jun 1, 2026
Updated 1d ago

Evaluation Results

MethodLinks
2026.06
65.56
2026.06
63.33
2026.06
60
2026.04
51.74
2026.06
51.1
2026.04
46.92
2026.04
45.31
2026.04
44.81
2026.04
44.78
2026.04
40.06
2026.04
31.87
2026.06
20
2026.06
20
2026.06
20
2026.06
20
2026.06
20
2026.06
16.7
2026.06
16.67
2026.06
16.67
2026.06
16.67
2026.06
16.67
2026.06
16.67
2026.06
13.33
2026.06
6.67
2025.04
5.33
2026.04
4.17
2026.04
4.17
2025.04
4
2026.04
3.75
2026.04
3.33
2026.04
3.33
2025.04
3.33
2025.04
3.33
2025.04
3.33
2025.04
2.67
2025.04
2
2025.04
2
2025.04
2
2026.04
1.67
2026.04
0.68