List your company

General Question Answering on Natural Questions (NQ) v1.0 (test)

40.4Exact MatchReCal
7.95216.37624.833.224Jun 10, 2026

Evaluation results

MethodLinks
ReCalRouting Strategy=RL-based Routing, Task Decomposition=false2026.0640.4
ReCal+Routing Strategy=RL-based Routing, Task Decomposition=false2026.0639
Router-R1Routing Strategy=RL-based Routing, Task Decomposition=false2026.0633.4
Search-R1Routing Strategy=No Routing, Task Decomposition=false2026.0632.8
Prompt LLMRouting Strategy=Heuristic & Discriminative Routing, Task Decomposition=false2026.0630
RAGRouting Strategy=No Routing, Task Decomposition=false2026.0629.8
Largest LLMRouting Strategy=Heuristic & Discriminative Routing, Task Decomposition=false2026.0629.6
RouterDCRouting Strategy=Heuristic & Discriminative Routing, Task Decomposition=false2026.0627.8
GraphRouterRouting Strategy=Heuristic & Discriminative Routing, Task Decomposition=false2026.0627.6
KNN RouterRouting Strategy=Heuristic & Discriminative Routing, Task Decomposition=false2026.0626.2
Prompt LLMRouting Strategy=Heuristic & Discriminative Routing, Task Decomposition=true2026.0625.8
MLP RouterRouting Strategy=Heuristic & Discriminative Routing, Task Decomposition=false2026.0625.2
KNN RouterRouting Strategy=Heuristic & Discriminative Routing, Task Decomposition=true2026.0623.6
RouteLLMRouting Strategy=Heuristic & Discriminative Routing, Task Decomposition=false2026.0623
SFTRouting Strategy=No Routing, Task Decomposition=false2026.0621.2
CoTRouting Strategy=No Routing, Task Decomposition=false2026.0612.6
VanillaRouting Strategy=No Routing, Task Decomposition=false2026.069.2