Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Long-context retrieval on RULER-NIAH 32k
Loading...
100
Accuracy
BF16
-4
23
50
77
May 18, 2026
Accuracy
Updated 14d ago
Evaluation Results
Method
Method
Links
Accuracy
BF16
Backbone=GLM-4.7-FP8†
2026.05
100
QuaRot-INT2
Backbone=GLM-4.7-FP8†
2026.05
100
OSCAR
Backbone=GLM-4.7-FP8†
2026.05
100
BF16
Backbone=Qwen3-4B-Thin...
2026.05
99.3
BF16
Backbone=Qwen3-8B
2026.05
97.3
OSCAR
Backbone=Qwen3-4B-Thin...
2026.05
87.6
OSCAR
Backbone=Qwen3-8B
2026.05
86.3
QuaRot-INT2
Backbone=Qwen3-8B
2026.05
9.8
QuaRot-INT2
Backbone=Qwen3-4B-Thin...
2026.05
0
Feedback
Search any
task
Search any
task