Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Question Answering on NQ (EM, ATC) benchmark leaderboard · SOTA2 Research

Research Benchmarks

Question Answering on NQ (EM, ATC)

40.3EMAdaTIR

Updated 5mo ago

Evaluation Results

Method	Links
AdaTIR2026.01		40.3	0.94
Search-R12026.01		39.1	1

SOTA Paper

AdaTIR

AdaTIR: Adaptive Tool-Integrated Reasoning via Difficulty-Aware Policy Optimization

Dataset

NQ

Follow for updates

Join SOTA2 Contact

Related Benchmarks

Question Answering on Musique Mathematical Reasoning on AIME 2024 (Avg@16 Accuracy and ATC)Mathematical Reasoning on AIME 2025 (Avg@16 Accuracy, ATC)Mathematical Reasoning on AMC 23 (Avg@16 Accuracy, Average Tool Calls (ATC))Mathematical Reasoning on GSM8K (Avg@16 Accuracy & ATC)