Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

MemoryBench Task on MemoryBench Long-Input-Long-Output

64.23Norm-Score

UNO

22.6333.4344.2355.03Feb 6, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.02
64.2317.74
2026.02
63.7715.66
2026.02
63.4114.87
2026.02
62.248.98
2026.02
62.047.58
2026.02
61.656.87
2026.02
61.496.5
2026.02
60.552.22
2026.02
59.09-4.3
2026.02
58.29-5.7
2026.02
57.95-7.71
2026.02
57.84-13.62
2026.02
57.14-17.1
2026.02
57.07-17.36
2026.02
55.63-24.44
2026.02
54.43-28.63
2026.02
53.71-31.43
2026.02
53.67-31.6
2026.02
53.22-32.94
2026.02
52.54-36.95
2026.02
52.23-37.53
2026.02
47.72-54.9
2026.02
45.96-59.89
2026.02
24.23-161.25