Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-hop QA on HotpotQA (test)
Loading...
45.2
Exact Match (EM)
ParetoPO
17.536
24.718
31.9
39.082
Jun 15, 2026
Exact Match (EM)
Tool Usage Rate (#Tool)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Exact Match (EM)
Tool Usage Rate (#Tool)
ParetoPO
Tool Use=Yes, Base Mod...
2026.06
45.2
0.9
ParetoPO
Tool Use=Yes, Base Mod...
2026.06
42.2
1.2
OTC-GRPO
Tool Use=Yes, Base Mod...
2026.06
36.6
1
OTC-GRPO
Tool Use=Yes, Base Mod...
2026.06
36.5
1.4
Search-R1
Tool Use=Yes, Base Mod...
2026.06
34.1
2.1
MO-GRPO
Tool Use=Yes, Base Mod...
2026.06
33.1
1.6
MO-GRPO
Tool Use=Yes, Base Mod...
2026.06
32
1.9
Search-R1
Tool Use=Yes, Base Mod...
2026.06
31.2
1.8
RAG
Tool Use=Yes, Base Mod...
2026.06
29.9
1
RAG
Tool Use=Yes, Base Mod...
2026.06
25.5
1
R1-Base
Tool Use=No, Base Mode...
2026.06
24.2
-
SFT
Tool Use=No, Base Mode...
2026.06
21.7
-
R1-Base
Tool Use=No, Base Mode...
2026.06
20.1
-
SFT
Tool Use=No, Base Mode...
2026.06
18.6
-
Feedback
Search any
task
Search any
task
