List your company

Retrieval-Augmented Question Answering on DeepSearch NQ

86SRSynapse
6.9627.484868.52Apr 13, 2026

Evaluation results

MethodLinks
SynapseTaskExecutor=Gemini-3.0-flash2026.048653.6
SynapseTaskExecutor=gpt-4o-mini, Category=Baselines & Retrieval-Based Memory2026.045238.6
SynapseTaskExecutor=gpt-4o2026.044838.9
SynapseTaskExecutor=Gemini-2.5-flash2026.044281.4
Gemini-3.0-flashTaskExecutor=gpt-4o-mini, Category=Zero-Shot Curators2026.04348
ActiveContextTaskExecutor=Gemini-3.0-flash2026.04326.8
Full ContextTaskExecutor=Gemini-3.0-flash2026.043062.4
gpt-4oTaskExecutor=gpt-4o-mini, Category=Zero-Shot Curators2026.043011.2
ActiveContextTaskExecutor=gpt-4o2026.04287.2
Gemini-2.5-flashTaskExecutor=gpt-4o-mini, Category=Zero-Shot Curators2026.04287.9
gpt-4o-miniTaskExecutor=gpt-4o-mini, Category=Zero-Shot Curators2026.042811.2
ContextCuratorTaskExecutor=gpt-4o-mini, Category=RL-Trained Curator2026.04287
ActiveContextTaskExecutor=Gemini-2.5-flash2026.0427.98.1
Training-Free GRPOTaskExecutor=gpt-4o2026.042635.3
AWMTaskExecutor=gpt-4o-mini, Category=Baselines & Retrieval-Based Memory2026.042439.1
Mem0TaskExecutor=gpt-4o-mini, Category=Baselines & Retrieval-Based Memory2026.042346.7
Training-Free GRPOTaskExecutor=Gemini-3.0-flash2026.042278.2
Full ContextTaskExecutor=Gemini-2.5-flash2026.042238.2
Full ContextTaskExecutor=gpt-4o2026.042240.8
Qwen2.5-7B-InstructTaskExecutor=gpt-4o-mini, Category=Zero-Shot Curators2026.042210.7
Full ContextTaskExecutor=gpt-4o-mini, Category=Baselines & Retrieval-Based Memory2026.042035.5
Training-Free GRPOTaskExecutor=gpt-4o-mini, Category=Baselines & Retrieval-Based Memory2026.042040.1
Training-Free GRPOTaskExecutor=Gemini-2.5-flash2026.041081.2