Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-hop Question Answering on SynthWorlds-RM
Loading...
26.9
Exact Match (EM)
Search-R1
12.652
16.351
20.05
23.749
Jun 4, 2026
Exact Match (EM)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Exact Match (EM)
Search-R1
Training Paradigm=RL-t...
2026.06
26.9
ReAct
Training Paradigm=Trai...
2026.06
22.2
SARDI
Training Paradigm=Trai...
2026.06
21.7
SARDI
Training Paradigm=Trai...
2026.06
21.1
AR W/ RET@1
Training Paradigm=Trai...
2026.06
20.4
AR W/ RET@10
Training Paradigm=Trai...
2026.06
19.3
AR W/ RET@STATIC
Training Paradigm=Trai...
2026.06
16.5
AR W/ RET@ADAPTIVE
Training Paradigm=Trai...
2026.06
15.7
DLM W/ RET@STATIC
Training Paradigm=Trai...
2026.06
14.4
AdaptiveRAG
Training Paradigm=Trai...
2026.06
13.2
Feedback
Search any
task
Search any
task