---
format: "aidr-story-markdown/v1"
id: "af81e03f025b5bf262054593f7bc636fb084bb3c4cf77d101f2f12ade9b6813d"
canonical_url: "https://aidr.today/af81e03f?lang=en"
title: "Opus 5.5 Tops AlphaXiv's First Open Benchmark for AI Autoresearch"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-11-20T22:07:10.000Z"
category: "Models"
topics: ["llm"]
source_urls: ["https://marketbrief.now/ai/update-opus-55-tops-alphaxivs-first-open-benchmark-for-ai-autoresearch-aeadac61","https://huggingnews.com/ai/update-opus-55-tops-alphaxivs-first-open-benchmark-for-ai-autoresearch-aeadac61"]
summary: "AlphaXiv has released the OpenResearch Intelligence Index, an open-source benchmark designed to measure end-to-end scientific research performance in AI models. Opus 5.5 achieved the highest score of 61.8% among eight evaluated models. The benchmark follows the launch of an AlphaXiv preprint server where autonomous agents produced 936 research papers over three months."
---

# Opus 5\.5 Tops AlphaXiv's First Open Benchmark for AI Autoresearch

> [Open the canonical story](<https://aidr.today/af81e03f?lang=en>)

**Published:** 2026-11-20T22:07:10.000Z
**Category:** Models
**Topics:** llm

## Summary

AlphaXiv has released the OpenResearch Intelligence Index, an open\-source benchmark designed to measure end\-to\-end scientific research performance in AI models\. Opus 5\.5 achieved the highest score of 61\.8% among eight evaluated models\. The benchmark follows the launch of an AlphaXiv preprint server where autonomous agents produced 936 research papers over three months\.

## Sources

- [Story source](<https://marketbrief.now/ai/update-opus-55-tops-alphaxivs-first-open-benchmark-for-ai-autoresearch-aeadac61>)
- [Story source](<https://huggingnews.com/ai/update-opus-55-tops-alphaxivs-first-open-benchmark-for-ai-autoresearch-aeadac61>)

