Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Long-context Retrieval and Reasoning on RULER 32k
Loading...
62.28
Score
Qwen3-4B
42.6864
47.7732
52.86
57.9468
Apr 24, 2026
Score
Updated 2mo ago
Evaluation Results
Method
Method
Links
Score
Qwen3-4B
Model Scale=4B
2026.04
62.28
Qwen2.5-3B
Model Scale=3B
2026.04
58.95
Llama3.2-3B
Model Scale=3B
2026.04
51.38
SpB2.0-5B
Model Scale=5B, Additi...
2026.04
50.87
Gemma3-4B
Model Scale=4B
2026.04
43.44
Feedback
Search any
task
Search any
task