List your company

ResearchFormerly WizWand

Long-term conversational Question Answering

Benchmarks

DatasetSOTA methodMetricTrendResultsLast updated

97.14SS User Accuracy

14

Jun 30, 2026

LoCoMo10 (test)

31Multi-Hop Accuracy

5

Apr 21, 2026

LongMemEval 90K-token dialogue history + 300-turn conversation

46.2QA Accuracy

3

May 21, 2026