Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-Hop QA on 2Wiki (Accuracy)
Loading...
70.5
Accuracy
SLEA-RL
14.028
28.689
43.35
58.011
Mar 18, 2026
Accuracy
Updated 29d ago
Evaluation Results
Method
Method
Links
Accuracy
SLEA-RL
Base Model=Qwen2.5-7B-...
2026.03
70.5
IGPO
Base Model=Qwen2.5-7B-...
2026.03
68.2
GSPO
Base Model=Qwen2.5-7B-...
2026.03
60.1
PPO
Base Model=Qwen2.5-7B-...
2026.03
59.7
GRPO
Base Model=Qwen2.5-7B-...
2026.03
57.7
RLOO
Base Model=Qwen2.5-7B-...
2026.03
55
Reinforce++
Base Model=Qwen2.5-7B-...
2026.03
54.5
GiGPO
Base Model=Qwen2.5-7B-...
2026.03
43.6
SkillRL
Base Model=Qwen2.5-7B-...
2026.03
43.2
EvolveR
Base Model=Qwen2.5-7B-...
2026.03
38.2
Search-R1
Base Model=Qwen2.5-7B-...
2026.03
37
ZeroSearch
Base Model=Qwen2.5-7B-...
2026.03
34.6
RAG
Base Model=Qwen2.5-7B-...
2026.03
25.8
R1-Instruct
Base Model=Qwen2.5-7B-...
2026.03
20.8
Search-o1
Base Model=Qwen2.5-7B-...
2026.03
17
Qwen2.5
Base Model=Qwen2.5-7B-...
2026.03
16.4
CoT
Base Model=Qwen2.5-7B-...
2026.03
16.2
Feedback
Search any
task
Search any
task