List your company

Single-Hop QA on NQ

48.5AccuracySLEA-RL
10.12420.08730.0540.013Mar 18, 2026

Evaluation results

MethodLinks
SLEA-RLBase Model=Qwen2.5-7B-Instruct, Method Category=RL Methods2026.0348.5
IGPOBase Model=Qwen2.5-7B-Instruct, Method Category=RL Methods2026.0346.7
GiGPOBase Model=Qwen2.5-7B-Instruct, Method Category=RL Methods2026.0346.4
SkillRLBase Model=Qwen2.5-7B-Instruct, Method Category=RL Methods2026.0345.9
ZeroSearchBase Model=Qwen2.5-7B-Instruct, Method Category=Prompting2026.0343.6
EvolveRBase Model=Qwen2.5-7B-Instruct, Method Category=Prompting2026.0343.5
GSPOBase Model=Qwen2.5-7B-Instruct, Method Category=RL Methods2026.0341.5
RLOOBase Model=Qwen2.5-7B-Instruct, Method Category=RL Methods2026.0340.7
GRPOBase Model=Qwen2.5-7B-Instruct, Method Category=RL Methods2026.0340.3
Search-R1Base Model=Qwen2.5-7B-Instruct, Method Category=Prompting2026.0339.3
PPOBase Model=Qwen2.5-7B-Instruct, Method Category=RL Methods2026.0338.7
Reinforce++Base Model=Qwen2.5-7B-Instruct, Method Category=RL Methods2026.0334.3
RAGBase Model=Qwen2.5-7B-Instruct, Method Category=Prompting2026.0327.4
R1-InstructBase Model=Qwen2.5-7B-Instruct, Method Category=Prompting2026.0321
Search-o1Base Model=Qwen2.5-7B-Instruct, Method Category=Prompting2026.0319.4
CoTBase Model=Qwen2.5-7B-Instruct, Method Category=Prompting2026.0312.8
Qwen2.5Base Model=Qwen2.5-7B-Instruct, Method Category=Prompting2026.0311.6