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

Reasoning on HLE (Score)

64.7Score

Claude Mythos Preview

-2.58814.88132.3549.819Jun 14, 2025Aug 17, 2025Oct 20, 2025Dec 24, 2025Feb 26, 2026May 1, 2026Jul 5, 2026
Updated 18d ago

Evaluation Results

MethodLinks
2025.06
64.7
2025.06
59.6
2025.06
58.7
2025.06
58.4
2025.06
57.2
2025.06
55.2
2025.06
55
2025.06
54.7
2025.06
54
2025.06
53.4
2025.06
53.1
2025.06
53
2025.06
52.2
2025.06
52.1
2025.06
51.4
2025.06
50.4
2025.06
50.2
2025.06
50
2025.06
49
2025.06
48.2
2025.06
48
2025.06
48
2025.06
46.4
45.8
2025.06
45.8
43.2
2026.05
37.2
2026.05
35.2
2026.05
32.9
2026.05
26.6
2026.05
24.6
2026.05
19.6
17.9
2026.06
17
2026.06
16.5
2026.06
16
2026.07
16
15.9
2025.12
14.8
2026.06
14.7
2025.12
14.6
13.3
2025.12
13.3
2026.06
12.6
2026.06
11
2026.06
10.8
2025.12
10.6
2026.06
9.5
2026.06
9.2
2026.06
7.1
2026.06
6.4
2026.06
6.3
2026.06
6.1
2025.10
5.58
2026.06
5.5
2026.06
5.4
2025.10
5.21
2025.10
5.21
2026.06
5.2
2025.10
5.14
2025.10
4.2
2025.10
4.13
2025.10
2.22
2026.06
0
2026.06
0