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

Reasoning on ANLI R3 benchmark leaderboard · SOTA2 Research

Research Benchmarks

Reasoning on ANLI R3

48.25AccuracyGANPO

Updated 5mo ago

Evaluation Results

Method	Links
GANPO2026.01		48.25
DPO2026.01		47.92
Base2026.01		47.75

SOTA Paper

GANPO

Latent Adversarial Regularization for Offline Preference Optimization

Dataset

ANLI

Follow for updates

Join SOTA2 Contact

Related Benchmarks

Preference Alignment on AlpacaEval weighted gpt4 turbo 2.0