Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Knowledge Probing on NQ-Open
Loading...
28.8
Exact Match (EM)
Baseline
21.4368
23.3484
25.26
27.1716
Jun 4, 2026
Exact Match (EM)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Exact Match (EM)
Baseline
Model=Qwen3-4B
2026.06
28.8
LRS
Model=Qwen3-4B
2026.06
26.78
ERSS
Model=Qwen3-4B
2026.06
25.24
ALRR
Model=Qwen3-4B
2026.06
25.18
Baseline
Model=R1-Distilled-LLa...
2026.06
23.24
ERSS
Model=R1-Distilled-LLa...
2026.06
22.3
LRS
Model=R1-Distilled-LLa...
2026.06
22.05
ALRR
Model=R1-Distilled-LLa...
2026.06
21.72
Feedback
Search any
task
Search any
task
