---
format: "aidr-story-markdown/v1"
id: "87f0ddfd825b26d67c742459daa656caba3e27fc445227c34749398317a469e9"
canonical_url: "https://aidr.today/87f0ddfd?lang=en"
title: "SO-Arena: Benchmarking the Capability Spectrum and Reliability of System One Models"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-11-13T00:00:00.000Z"
category: "Research"
topics: ["llm"]
source_urls: ["https://huggingface.co/papers/2611.15777"]
summary: "SO-Arena is a benchmark characterizing the capability spectrum and decision reliability of System One models across 11 domains and five capability families. SO-Arena offers evidence-grounded evaluation and fine-grained capability assessment through domain-specific difficulty criteria. Decision reliability is assessed through decision stability under controlled option-set changes and missing-answer recognition when no valid option is available."
---

# SO\-Arena: Benchmarking the Capability Spectrum and Reliability of System One Models

> [Open the canonical story](<https://aidr.today/87f0ddfd?lang=en>)

**Published:** 2026-11-13T00:00:00.000Z
**Category:** Research
**Topics:** llm

## Summary

SO\-Arena is a benchmark characterizing the capability spectrum and decision reliability of System One models across 11 domains and five capability families\. SO\-Arena offers evidence\-grounded evaluation and fine\-grained capability assessment through domain\-specific difficulty criteria\. Decision reliability is assessed through decision stability under controlled option\-set changes and missing\-answer recognition when no valid option is available\.

## Sources

- [Story source](<https://huggingface.co/papers/2611.15777>)