A new human-curated benchmark for LLM mobile assistants shows models struggle to locate scattered personal information, with the best model at 57.3% accuracy.
Gaia2: Benchmarking
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SPIEval: Evaluating Large Language Models as Mobile Assistants over Scattered Personal Information
A new human-curated benchmark for LLM mobile assistants shows models struggle to locate scattered personal information, with the best model at 57.3% accuracy.