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

Multi-Hop Reasoning on LoCoMo

41.62F1 Score

R2-Mem

0.467211.151121.83532.5189Apr 14, 2026Apr 18, 2026Apr 23, 2026Apr 28, 2026May 3, 2026May 8, 2026May 13, 2026
Updated 20d ago

Evaluation Results

MethodLinks
2026.05
41.6232.34
2026.05
38.0929.02
2026.05
37.7529.28
2026.04
36.6629.06
2026.05
36.5528.71
2026.05
36.2327.71
2026.04
35.8827.96
2026.05
35.3626.43
2026.04
35.3225.77
2026.04
35.2725.22
2026.04
33.3225.38
2026.04
32.8623.99
2026.04
32.7820.87
2026.04
31.4524.59
2026.04
29.3721.4
2026.04
28.7422.35
2026.04
28.4921.21
2026.05
27.5518.91
2026.04
27.5118.51
2026.04
27.4619.14
2026.04
27.0220.09
2026.05
26.7217.9
2026.04
26.6517.72
2026.04
26.5516.56
2026.05
24.4218.66
2026.05
23.6915.28
2026.05
23.4517.61
2026.05
22.5916.28
2026.04
21.8513.4
2026.04
21.0313.75
2026.05
20.4315.76
2026.04
20.1612.67
2026.04
20.0616.22
2026.05
19.2314.17
2026.04
19.0611.71
2026.04
18.2311.94
2026.04
17.4411.74
2026.04
17.4411.74
2026.05
13.2910.66
2026.04
13.1810.03
2026.05
12.8411.02
2026.04
12.579.01
2026.04
11.259.18
2026.04
11.148.25
2026.04
10.447.61
2026.04
9.196.96
2026.04
9.156.48
2026.04
9.056.55
2026.04
8.375.42
2026.04
7.595.09
2026.04
7.355.34
2026.04
6.885.77
2026.04
6.614.93
2026.04
6.225.39
2026.04
6.194.47
2026.04
6.174.97
2026.04
5.965.12
2026.04
5.374.02
2026.04
5.323.99
2026.04
5.074.31
2026.04
54.77
2026.04
4.614.29
2026.04
4.332.99
2026.04
3.653.16
2026.04
3.63.39
2026.04
2.471.78
2026.04
2.471.78
2026.04
2.051.96