List your company

Single-Hop Question Answering on TriviaQA (out-of-domain)

68AccuracyGEPO
34.30443.05251.860.548Oct 30, 2025Nov 16, 2025Dec 3, 2025Dec 20, 2025Jan 6, 2026Jan 23, 2026Feb 9, 2026

Evaluation results

MethodLinks
GEPOType=RL Training, Model=Qwen2.5-7B-Instruct2025.1068
GEPOType=RL Training, Model=Qwen2.5-3B-Instruct2025.1065.2
GiGPOType=RL Training, Model=Qwen2.5-7B-Instruct2025.1064.7
EvolveRBackbone=Qwen2.5-7B-Instruct2026.0263.4
SKILLRLBackbone=Qwen2.5-7B-Instruct2026.0263.3
ZeroSearchBackbone=Qwen2.5-7B-Instruct2026.0261.8
ZeroSearchType=RL Training, Model=Qwen2.5-7B-Instruct2025.1061.8
Search-R1Backbone=Qwen2.5-7B-Instruct2026.0261
Search-R1Type=RL Training, Model=Qwen2.5-7B-Instruct2025.1061
GiGPOType=RL Training, Model=Qwen2.5-3B-Instruct2025.1059.5
RAGBackbone=Qwen2.5-7B-Instruct2026.0258.2
ZeroSearchType=RL Training, Model=Qwen2.5-3B-Instruct2025.1057.4
Search-R1Type=RL Training, Model=Qwen2.5-3B-Instruct2025.1054.5
R1-InstructType=RL Training, Model=Qwen2.5-3B-Instruct2025.1053.7
R1-InstructBackbone=Qwen2.5-7B-Instruct2026.0244.9
R1-InstructType=RL Training, Model=Qwen2.5-7B-Instruct2025.1044.9
Search-o1Backbone=Qwen2.5-7B-Instruct2026.0240.6
Qwen2.5Backbone=Qwen2.5-7B-Instruct2026.0235.6
CoTBackbone=Qwen2.5-7B-Instruct2026.0235.6