List your company
ResearchFormerly WizWand

Question Answering on QASPER 1200:251 (test)

28.92Answerable EMQwen3-4B
-1.15686.651614.4622.2684Jan 8, 2026
Updated 8mo ago

Evaluation results

MethodLinks
Qwen3-4BTraining Paradigm=SFT based, Backbone=Qwen3-4B, Retriever Config=k=3, Embedding Model=Qwen3-Embedding-0.6B2026.0128.9269.5362.2567.3367.3363.1364.79
Llama3-8B-InstructTraining Paradigm=SFT based, Backbone=Llama3-8B-Instruct, Retriever Config=k=3, Embedding Model=Qwen3-Embedding-0.6B2026.0127.9270.2162.7562.9562.9562.7862.85
GRACE-Qwen3-4BTraining Paradigm=Our methods, Backbone=Qwen3-4B, Retriever Config=k=3, Embedding Model=Qwen3-Embedding-0.6B2026.0127.0873.0974.2574.974.974.3674.58
GRACE-Llama3.1-8BTraining Paradigm=Our methods, Backbone=Llama3.1-8B, Retriever Config=k=3, Embedding Model=Qwen3-Embedding-0.6B2026.0127.0872.0270.0874.574.570.8572.29
ARENA-8BTraining Paradigm=RL based, Backbone=ARENA-8B, Checkpoint Status=released (†), Retriever Config=k=3, Embedding Model=Qwen3-Embedding-0.6B2026.0123.5868.6669.1700.457.2734.79
ARENA on Qwen3-4BTraining Paradigm=RL based, Method Strategy=ARENA, Backbone=Qwen3-4B, Retriever Config=k=3, Embedding Model=Qwen3-Embedding-0.6B2026.0123.2568.0873.519.9220.7264.3747.11
SimpleDeepSearcher-7BTraining Paradigm=Agentic Models, Backbone=SimpleDeepSearcher-7B, Checkpoint Status=released (†), Retriever Config=k=3, Embedding Model=Qwen3-Embedding-0.6B2026.0122.9267.1367.1716.7317.9358.6542.55
ARENA-7BTraining Paradigm=RL based, Backbone=ARENA-7B, Checkpoint Status=released (†), Retriever Config=k=3, Embedding Model=Qwen3-Embedding-0.6B2026.0122.569.7369.674.787.9758.9938.82
Search-R1-7BTraining Paradigm=Agentic Models, Backbone=Search-R1-7B, Checkpoint Status=released (†), Retriever Config=k=3, Embedding Model=Qwen3-Embedding-0.6B2026.0118.564.766130.6833.0756.1747.03
R1-Searcher-7BTraining Paradigm=Agentic Models, Backbone=R1-Searcher-7B, Checkpoint Status=released (†), Retriever Config=k=3, Embedding Model=Qwen3-Embedding-0.6B2026.0115.4259.848.8317.1319.9243.8334.38
SuRe on DeepSeek-chatTraining Paradigm=Prompt based, Method Strategy=SuRe, Backbone=DeepSeek-chat, Retriever Config=k=3, Embedding Model=Qwen3-Embedding-0.6B2026.0113.0858.6857.9207.1749.1432.54
SuRe on Qwen3-4BTraining Paradigm=Prompt based, Method Strategy=SuRe, Backbone=Qwen3-4B, Retriever Config=k=3, Embedding Model=Qwen3-Embedding-0.6B2026.015.9252.4346.1700.438.2523.28
SuRe on Llama3-8B-InstructTraining Paradigm=Prompt based, Method Strategy=SuRe, Backbone=Llama3-8B-Instruct, Retriever Config=k=3, Embedding Model=Qwen3-Embedding-0.6B2026.015.2555.0154.8301.5945.6228.21
Llama3-8B-InstructTraining Paradigm=Prompt based, Backbone=Llama3-8B-Instruct, Retriever Config=k=3, Embedding Model=Qwen3-Embedding-0.6B2026.011.3354.670.5812.7530.6863.6850.63
TrustAlign-8BTraining Paradigm=RL based, Backbone=TrustAlign-8B, Checkpoint Status=released (†), Retriever Config=k=3, Embedding Model=Qwen3-Embedding-0.6B2026.010.0834.729.6797.6197.6124.8853.64
Qwen3-4BTraining Paradigm=Prompt based, Backbone=Qwen3-4B, Retriever Config=k=3, Embedding Model=Qwen3-Embedding-0.6B2026.01050.2378.835.5842.2372.560.53
DeepSeek-chatTraining Paradigm=Prompt based, Backbone=DeepSeek-chat, Retriever Config=k=3, Embedding Model=Qwen3-Embedding-0.6B2026.01051.8869.3350.672.1169.8169.57
TrustAlign-3BTraining Paradigm=RL based, Backbone=TrustAlign-3B, Checkpoint Status=released (†), Retriever Config=k=3, Embedding Model=Qwen3-Embedding-0.6B2026.01041.241.1778.0980.8848.0461.03
TrustAlign on Qwen3-4BTraining Paradigm=RL based, Method Strategy=TrustAlign, Backbone=Qwen3-4B, Retriever Config=k=3, Embedding Model=Qwen3-Embedding-0.6B2026.01044.536.83060.9641.0148.9
TrustAlign-7BTraining Paradigm=RL based, Backbone=TrustAlign-7B, Checkpoint Status=released (†), Retriever Config=k=3, Embedding Model=Qwen3-Embedding-0.6B2026.01043.6333.67088.4543.1438.41