List your company

ResearchFormerly WizWand

Multi-paper Question Answering

Benchmarks

DatasetSOTA methodMetricTrendResultsLast updated

ScholarQABench Multi

Llama 3.1 8B Instruct

4.32Mean Score

16

Apr 3, 2026

NLP-MQA annotated (test)

78.3Precision

11

Feb 26, 2026