SPIEval

What is SPIEval?

SPIEval is a human-curated benchmark for evaluating large language models as mobile assistants that retrieve and reason over personal information scattered…

Released

2026-08-11

Evaluates

General AI, Language & Knowledge, Reasoning

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2608.10692

SPIEval paper and dataset

• Paper https://arxiv.org/abs/2608.10692
• Dataset https://huggingface.co/datasets/Junjie-Ye/SPIEval

Which sources cite SPIEval?

• SPIEval

Related General AI, Language & Knowledge, Reasoning benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• A-OKVQA
• A3S-Bench
• AARRI-Bench
• ABC-Bench