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

Attribution Faithfulness Evaluation research benchmarks · SOTA2 Research

Attribution Faithfulness Evaluation

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

SocialNetwork (test)

FT (Failure Taxonomy)

-0.1Risk Drop

50

Feb 26, 2026

TwinMarket (test)

Ours (Shapley-based framework)

7,790Risk Drop

50

Feb 26, 2026

EconAgent (test)

-86.35Risk Drop

50

Feb 26, 2026

ImageNet (test)

69.34Deletion Score

30

Mar 17, 2026

44MoRF

6

Apr 16, 2026

IFEval, EvalPlus, MATH, and GAIA2 60 failure cases

1.7Average Tokens to Fix

3

Apr 21, 2026

Popular datasets

ImageNet EconAgent TwinMarket SocialNetwork LongRA

Follow for updates

Join SOTA2 Contact