Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Long-context understanding on LongEval
Loading...
79
Score
FP
31.16
43.58
56
68.42
Feb 3, 2026
Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Score
FP
Model=Qwen2.5-32B, Com...
2026.02
79
SAES-SVD
Model=Qwen2.5-32B, Com...
2026.02
76
SVD-LLM
Model=Qwen2.5-32B, Com...
2026.02
73
ASVD
Model=Qwen2.5-32B, Com...
2026.02
61
FP
Model=Qwen2.5-7B, Comp...
2026.02
58
SAES-SVD
Model=Qwen2.5-7B, Comp...
2026.02
57
SVD-LLM
Model=Qwen2.5-7B, Comp...
2026.02
55
FP
Model=LLaMA3.1-70B, Co...
2026.02
49
ASVD
Model=Qwen2.5-7B, Comp...
2026.02
49
SAES-SVD
Model=LLaMA3.1-70B, Co...
2026.02
48
SVD-LLM
Model=LLaMA3.1-70B, Co...
2026.02
45
FP
Model=LLaMA3.1-8B, Com...
2026.02
41
SAES-SVD
Model=LLaMA3.1-8B, Com...
2026.02
39
ASVD
Model=LLaMA3.1-70B, Co...
2026.02
39
SVD-LLM
Model=LLaMA3.1-8B, Com...
2026.02
37
ASVD
Model=LLaMA3.1-8B, Com...
2026.02
33
Feedback
Search any
task
Search any
task
