Our new X account is live! Follow @wizwand_team for updates

Home/Benchmarks

Systematic Generalization on SCAN

100Accuracy

SKiC

Updated 3d ago

Evaluation Results

Method	Links
SKiC 2023.08		100
COT 2023.08		72.5

SOTA Paper

SKiC

Skills-in-Context Prompting: Unlocking Compositionality in Large Language Models

Dataset

SCAN

Follow for update

@wizwand_team Discord

Related Benchmarks

Multi-hop Reasoning on CommaQA-E (test)Multi-hop Reasoning on CommaQA-E compositional Last-letter-concatenation on Last-letter-concatenation 1 word (in-distribution)Last-letter-concatenation on Last-letter-concatenation 2 words (in-distribution)Last-letter-concatenation on Last-letter-concatenation 4 words (out-of-distribution)

© 2026 wizwand

Blog Contact Changelog

Privacy Policy Terms of Service FAQs