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

Natural Language Inference research benchmarks – Page 7 · SOTA2 Research

Natural Language Inference

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

CrossFit NLI (test)

83.6Accuracy

10

Apr 3, 2026

89.5Accuracy

10

Feb 26, 2026

ELECTRA base + PiFi

86.26Accuracy

10

Feb 26, 2026

MultiNLI matched/mismatched

Turing NLR v5 XXL

92.6Accuracy

10

Feb 26, 2026

IndicXNLI IndicXTREME (test)

0.423F1 Score

10

Feb 26, 2026

86.4Accuracy

10

Feb 26, 2026

86.54Accuracy

10

Feb 26, 2026

MNLI matched mismatched (dev)

84Accuracy (Matched)

10

Feb 26, 2026

72.59Macro-F1

9

May 27, 2026

HANS evaluated subset

MechaRule (Qwen2-1.5B)

157Rule-bearing

9

May 6, 2026

EXAONE-2.4B + SCRIPT

85.77Accuracy

9

Apr 15, 2026

79Accuracy (RTE)

9

Jun 4, 2026

NLI ANLI and HANS (unseen)

32.4ANLI Score

9

Apr 10, 2026

MNLI Matched (test)

90.2Accuracy

9

Mar 20, 2026

5.43Total Communication Time (10^3 s)

9

Feb 26, 2026

51.97Accuracy

9

Feb 26, 2026

58.42Accuracy

9

Feb 26, 2026

53.49Accuracy

9

Feb 26, 2026

MNLI mismatched (val)

75.01Accuracy

9

Feb 26, 2026

94Accuracy

9

Feb 26, 2026

AmericasNLI (test)

58.9Accuracy (aym)

9

Feb 26, 2026

IndicBERT v2 +Samanantar

74.3Accuracy

9

Feb 27, 2026

MNLI Mismatched Hard (test)

BERT-base + PoE

79.28Accuracy

9

Feb 26, 2026

MNLI Matched Hard (test)

BERT-base + PoE

80.03Accuracy

9

Feb 26, 2026

MNLI GLUE matched mismatched average (test)

84.8Accuracy

9

Feb 26, 2026

Page 7 of 15

Popular datasets

MNLI ANLI SNLI XNLI MultiNLI

Follow for updates

Join SOTA2 Contact