Paper Detail
Lichen Li, Ziping Dong, Sicheng Feng, Qi Li, Xinchao Wang
System One models promise fast, general-purpose decision-making without lengthy token generation. However, understanding their capability spectrum and decision reliability requires more than aggregate performance on current benchmarks. Existing evaluations often provide limited insight into the breadth of model capabilities and the reliability of their decisions. We introduce SO-Arena, a benchmark characterizing the capability spectrum and decision reliability of System One models across 11 domains and five capability families. For the capability spectrum, SO-Arena offers evidence-grounded evaluation through reliable sources and manual verification of reference labels against model-visible inputs; fine-grained capability assessment through domain-specific difficulty criteria; and realistic interactive evaluation, where models iteratively execute actions in sandboxes. Reasoning-intensive tasks further enable system one-two comparison. Beyond accuracy, SO-Arena assesses decision reliability through two complementary measures: decision stability under controlled option-set changes and missing-answer recognition when no valid option is available. Evaluations across 21 models reveal that the benefits of scaling and additional reasoning vary substantially across domains. More importantly, strong overall performance does not necessarily imply reliable decision-making: the best-performing System One model ranks only seventh in reliability. Together, these findings highlight the need to characterize capability spectrum and decision reliability as complementary dimensions, providing a systematic view of the strengths and limitations of System One models.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@misc{li2026so,
title = {SO-Arena: Benchmarking the Capability Spectrum and Reliability of System One Models},
author = {Lichen Li and Ziping Dong and Sicheng Feng and Qi Li and Xinchao Wang},
year = {2026},
abstract = {System One models promise fast, general-purpose decision-making without lengthy token generation. However, understanding their capability spectrum and decision reliability requires more than aggregate performance on current benchmarks. Existing evaluations often provide limited insight into the breadth of model capabilities and the reliability of their decisions. We introduce SO-Arena, a benchmark characterizing the capability spectrum and decision reliability of System One models across 11 doma},
url = {https://huggingface.co/papers/2611.15777},
keywords = {System One models, token generation, SO-Arena, capability spectrum, decision reliability, evidence-grounded evaluation, manual verification, reference labels, model-visible inputs, fine-grained capability assessment, domain-specific difficulty criteria, realistic interactive evaluation, sandboxes, reasoning-intensive tasks, system one-two comparison, decision stability, controlled option-set changes, missing-answer recognition, scaling, reasoning, code available, huggingface daily},
eprint = {2611.15777},
archiveprefix = {arXiv},
}
{}