List your company

ResearchFormerly WizWand

Sentence Classification

Benchmarks

DatasetSOTA methodMetricTrendResultsLast updated

SentEval Transfer Tasks (test)

90.53MR

73

Feb 26, 2026

Stanford Sentiment Treebank (SST) fine-grained (test)

53.1Accuracy

40

Feb 26, 2026

93.48Accuracy

33

Feb 26, 2026

90.8Accuracy

22

Jun 2, 2026

Combined dataset (K1, K2, K3, R4)

Qwen3.5 9B Multi-agent

76.9Precision

19

May 12, 2026

Amazon Review (test)

92.94Accuracy

15

Feb 26, 2026

IMDB full (test)

96.1Accuracy

9

Feb 27, 2026

Subj full (test)

97.4Accuracy

9

Feb 27, 2026

92.5Accuracy

9

Feb 27, 2026

90.53MNLI Accuracy

9

Feb 26, 2026

GLUE MNLI, QQP, QNLI, SST2 (Matched, Mismatched, dev)

85.91MNLI-m Accuracy

9

Feb 26, 2026

CoLA full (test)

86.4Accuracy

9

Feb 27, 2026

95.1Accuracy

9

Feb 27, 2026

92.5Accuracy

9

Feb 27, 2026

96.8Accuracy

9

Feb 26, 2026

Chart-To-Text (test)

92.38Accuracy

8

Feb 26, 2026

94.2Accuracy

7

Feb 26, 2026

90.3Accuracy

6

Feb 26, 2026

0.264F1 Score

6

Feb 26, 2026

MPQA (Multi-Perspective Question Answering) (10-fold cross-validation)

Skip-thought + LN

89Accuracy

4

Feb 26, 2026

Subj (Subjectivity) (10-fold cross-validation)

Skip-thought + LN

93.4Accuracy

4

Feb 26, 2026

CR (Customer Review) (10-fold cross-validation)

Skip-thought + LN

82.6Accuracy

4

Feb 26, 2026

MR (Movie Review) (10-fold cross-validation)

Skip-thought + LN

79.5Accuracy

4

Feb 26, 2026

84.7F1 Score

4

Feb 26, 2026

PubMed 200k (test)

93.9F1 Score

3

Feb 26, 2026