Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Long-context evaluation on RULER 256K
Loading...
100
NS1 (Sequence Accuracy 1)
Dense
95
97.5
100
102.5
Jun 3, 2025
NS1 (Sequence Accuracy 1)
NS2 (Sequence Accuracy 2)
NS3 (Sequence Accuracy 3)
NMK1 (Knowledge Recall 1)
NMK2 (Knowledge Recall 2)
NMV (Verification Score)
NMQ (Query Score)
VT Score
FWE Score
QA1 (Query Answering 1)
QA2 (Query Answering 2)
Average Score
Updated 4d ago
Evaluation Results
Method
Method
Links
NS1 (Sequence Accuracy 1)
NS2 (Sequence Accuracy 2)
NS3 (Sequence Accuracy 3)
NMK1 (Knowledge Recall 1)
NMK2 (Knowledge Recall 2)
NMV (Verification Score)
NMQ (Query Score)
VT Score
FWE Score
QA1 (Query Answering 1)
QA2 (Query Answering 2)
Average Score
Dense
Model=Qwen2.5-14B-Inst...
2025.06
100
100
100
100
90
85
97.5
100
95
60
40
87.95
top-k
Model=Qwen2.5-14B-Inst...
2025.06
100
100
100
100
90
81.25
98.75
100
88.33
60
40
87.12
HATA
Model=Qwen2.5-14B-Inst...
2025.06
100
100
100
100
95
85
97.5
96
85
60
45
88.05
Feedback
Search any
task
Search any
task
