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

Long-context reasoning on OOLONG trec_coarse

86.6Score

Kimi K2

-3.46419.91843.366.682Mar 3, 2026Mar 4, 2026Mar 5, 2026Mar 6, 2026Mar 7, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
86.6
2026.03
65.5
2026.03
60.7
2026.03
60
2026.03
56.5
2026.03
55
2026.03
53
2026.03
51.8
2026.03
50.5
2026.03
48
2026.03
46
2026.03
45.9
2026.03
45.7
2026.03
44.1
2026.03
44
2026.03
44
2026.03
42.1
2026.03
40
2026.03
39.1
2026.03
38
2026.03
38
2026.03
36
2026.03
36
2026.03
33.7
2026.03
32
2026.03
24
2026.03
0
2026.03
0