Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Long-context Evaluation on RULER (CWE Metric)
Loading...
1.23
Context Window Error (CWE)
Random
1.1152
1.8901
2.665
3.4399
Apr 17, 2026
Context Window Error (CWE)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Context Window Error (CWE)
Random
Target Model=Pythia-1B...
2026.04
1.23
Embed Sim
Target Model=Pythia-1B...
2026.04
1.8
Base Model
Target Model=Pythia-1B
2026.04
2.14
BM25
Target Model=Pythia-1B...
2026.04
2.34
TrackStar
Target Model=Pythia-1B...
2026.04
2.54
RISE
Target Model=Pythia-1B...
2026.04
4.1
Feedback
Search any
task
Search any
task