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

Accuracy and Avg on Reasoning on HLE

50.2Accuracy

Kimi-K2.5

7.97618.93829.940.862May 23, 2026
Updated 8d ago

Evaluation Results

MethodLinks
2026.05
50.2-
2026.05
49.565
2026.05
4457.6
2026.05
43.557.3
2026.05
43.4-
2026.05
4256
2026.05
4154.4
2026.05
37.248.7
2026.05
3445.2
2026.05
32.9-
2026.05
32.248.5
2026.05
31.549
2026.05
28.8-
2026.05
26.6-
2026.05
15.8-
2026.05
9.6-