Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-hop QA on NQ (test)
Loading...
50.1
EM
ParetoPO
21.5
28.925
36.35
43.775
Jun 15, 2026
EM
Tool Usage
Updated 1mo ago
Evaluation Results
Method
Method
Links
EM
Tool Usage
ParetoPO
Tool Use=Yes, Base Mod...
2026.06
50.1
0.9
ParetoPO
Tool Use=Yes, Base Mod...
2026.06
48
0.9
OTC-GRPO
Tool Use=Yes, Base Mod...
2026.06
44.4
1
OTC-GRPO
Tool Use=Yes, Base Mod...
2026.06
44.4
1
MO-GRPO
Tool Use=Yes, Base Mod...
2026.06
41.5
1.4
MO-GRPO
Tool Use=Yes, Base Mod...
2026.06
41.2
1.8
Search-R1
Tool Use=Yes, Base Mod...
2026.06
40.4
1.4
Search-R1
Tool Use=Yes, Base Mod...
2026.06
39.9
1.7
RAG
Tool Use=Yes, Base Mod...
2026.06
34.9
1
RAG
Tool Use=Yes, Base Mod...
2026.06
34.8
1
SFT
Tool Use=No, Base Mode...
2026.06
31.8
-
R1-Base
Tool Use=No, Base Mode...
2026.06
27
-
SFT
Tool Use=No, Base Mode...
2026.06
24.9
-
R1-Base
Tool Use=No, Base Mode...
2026.06
22.6
-
Feedback
Search any
task
Search any
task