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 14 · SOTA2 Research

Natural Language Inference

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

6 languages (Same script split)

45.2Accuracy

4

Feb 26, 2026

6 languages (Different script split)

42.4Accuracy

4

Feb 26, 2026

32.12Accuracy

4

Feb 26, 2026

83.21Accuracy

4

Feb 26, 2026

59.86Accuracy

4

Feb 26, 2026

65.82Accuracy

4

Feb 26, 2026

72.56Accuracy

4

Feb 26, 2026

89.11Accuracy

4

Feb 26, 2026

84.38Accuracy

4

Feb 26, 2026

13.6Training Throughput

4

Feb 26, 2026

ANLI all rounds (test)

58.2Accuracy

4

Feb 26, 2026

84.4Clean Accuracy

4

Feb 26, 2026

Glockner 2018 (test)

83.5Accuracy

4

Feb 26, 2026

XNLI German (test)

34.5Accuracy

4

Feb 26, 2026

contract_nli LegalBench

81.7Accuracy

3

Jun 11, 2026

80Accuracy

3

Jun 1, 2026

ContractNLI SCROLLS (test)

59.38Exact Match (EM)

3

May 22, 2026

RTE (out-of-distribution)

71.31Accuracy

3

May 14, 2026

VariErrNLI (test)

Prefixed Bridge Explainer

93.9F1 (Macro)

3

Apr 24, 2026

1B Model (Multilingual classifier)

56.1Accuracy (Normalized)

3

Apr 23, 2026

XNLI Spanish (test)

47.83Accuracy (Normalized)

3

Apr 23, 2026

61.2ANLI R1 EM

3

Apr 21, 2026

90.6Accuracy

3

Apr 10, 2026

AmericasNLI (dev)

48.8Accuracy (Aymara)

3

Mar 9, 2026

Krause-Llama3-8B

40.5Accuracy

3

Feb 26, 2026

Page 14 of 15

Popular datasets

MNLI ANLI SNLI XNLI MultiNLI

Follow for updates

Join SOTA2 Contact