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

Code Reasoning on CRUXEval-O

83.5Accuracy

Kimi-K2 Base

-3.3419.20541.7564.295May 26, 2025Jul 26, 2025Sep 25, 2025Nov 26, 2025Jan 26, 2026Mar 28, 2026May 29, 2026
Updated 1d ago

Evaluation Results

MethodLinks
2026.01
83.5
2026.05
80.5
2026.05
79.9
2026.01
79.1
2026.05
78.7
2026.05
78.1
2026.05
78.1
2026.05
78
2026.05
78
2026.05
77.8
2026.05
77.3
2026.05
77
2026.05
76.9
2026.01
76.4
2026.05
76.4
2026.05
76.3
2026.05
76.2
2026.05
76
2026.05
76
2026.05
75.8
2026.05
75.6
2026.05
75.6
2026.01
74.9
2026.05
74.7
2026.05
74.7
2026.05
74.7
2026.05
73.5
2026.05
71.9
2026.05
71.3
2026.05
71.3
2026.05
71.3
2026.05
71.3
2025.05
67.7
2025.05
66.3
2025.05
57.4
2026.02
56.5
2025.05
56
2026.02
55.88
2026.02
55.75
2026.02
55.5
2025.05
53.8
2025.05
52
2025.05
49.1
2026.05
43.9
2026.05
43.5
2026.05
43.2
2026.05
42.9
2025.05
41.6
2025.05
41.1
2026.05
36.6
2025.05
34.1
2025.05
32.8
2025.05
29.9
2025.05
29.6
2026.02
25.62
2025.05
23.6
2025.05
17.8
2026.02
5.25
2026.02
5.12
2026.02
3.38
2025.05
0