Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Mathematical Reasoning on AIME 2025 (Acc, Delay, TTFT)

77Acc

Baseline (Thinking)

-1.343218.995939.33559.6741Oct 1, 2025Oct 12, 2025Oct 24, 2025Nov 5, 2025Nov 17, 2025Nov 29, 2025Dec 11, 2025
Updated 4d ago

Evaluation Results

MethodLinks
2025.12
77326.525,079.68
2025.12
685,348.225,330.46
2025.12
68500.949.06
2025.12
671,814.091,813.67
2025.12
66166.7524.63
2025.12
625.25.2
2025.12
62523.537,691.55
2025.12
59147.9624.15
2025.12
531,915.21,914.45
2025.12
5320.169.73
2025.12
5191.41,411.24
2025.12
49485.935.41
2025.12
395.255.25
2025.12
36120.091,694.43
2025.10
32.63--
2025.10
31.8--
2025.10
31.25--
2025.10
30--
2025.10
29.75--
2025.10
28.89--
2025.10
27.25--
2025.10
24.17--
2025.10
23.89--
2025.10
23.75--
2025.10
23.33--
2025.10
22.67--
2025.10
21.5--
2025.10
21.11--
2025.12
201.71.13
2025.10
20--
2025.10
20--
2025.10
20--
2025.10
19.33--
2025.10
18.33--
2025.10
17--
2025.10
15.33--
2025.10
15.06--
2025.10
15.05--
2025.10
13.33--
2025.10
12.5--
2025.10
11.67--
2025.10
11.67--
2025.10
11.67--
2025.10
11.67--
2025.10
11.11--
2025.10
10.17--
2025.10
8.33--
2025.10
7.5--
2025.10
7.5--
2025.10
7.5--
2025.10
6.67--
2025.10
5.5--
2025.10
3.33--
2025.10
1.67--