Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Long-Context Retrieval on RULER (4K to 256K Sweep)
Loading...
95.9
Retrieval Accuracy (4K Context)
INF-V2
92.156
93.128
94.1
95.072
Jan 29, 2026
Retrieval Accuracy (4K Context)
Retrieval Accuracy (8K Context)
Retrieval Accuracy (16K Context)
Retrieval Accuracy (32K Context)
Retrieval Accuracy (64K Context)
Retrieval Accuracy (128K Context)
Retrieval Accuracy (256K Context)
Updated 4d ago
Evaluation Results
Method
Method
Links
Retrieval Accuracy (4K Context)
Retrieval Accuracy (8K Context)
Retrieval Accuracy (16K Context)
Retrieval Accuracy (32K Context)
Retrieval Accuracy (64K Context)
Retrieval Accuracy (128K Context)
Retrieval Accuracy (256K Context)
INF-V2
Full name=InfLLM-v2, A...
2026.01
95.9
94.1
92.1
89.3
86.7
61.6
42.6
SPA
Description=Ablation v...
2026.01
95.9
94.2
93.3
90.4
87.1
62.4
44.5
SPLA
Full name=Block Sparse...
2026.01
95.9
94.7
94.2
91.7
88.3
85.2
72.3
DENSE
Attention=Full-attenti...
2026.01
95.8
94.9
93.6
91.4
87.1
83.2
69.3
NSA
Attention=Sparse atten...
2026.01
92.3
91.4
90.7
84.6
83.2
51.3
32.5
Feedback
Search any
task
Search any
task
