List your company

ResearchFormerly WizWand

Parsing

Benchmarks

DatasetSOTA methodMetricTrendResultsLast updated

LoRA-finetuned LLama-3.2-3B

92Accuracy

19

Apr 21, 2026

CRF (two-stage) w/o MBR

1,092Sents/sec

17

Feb 26, 2026

PASCAL-Context (test)

70.52mIoU

14

Feb 26, 2026

Generative RNNG, p(y | x)

86.9F1 Score

13

Feb 26, 2026

Wang et al. (2015)

86.6F1 Score

11

Feb 26, 2026

75.75mIoU

10

Feb 27, 2026

English PTB-SD 3.3.0 (test)

Kuncoro et al. (2016)

95.8UAS

7

Feb 26, 2026

89.23UAC

4

Feb 26, 2026

Chinese PTB 5.1 (test)

89.3UAS

4

Feb 26, 2026

300D SPINN (unparsed input) encoders

92.4Transition Acc

1

Feb 26, 2026