---
format: "aidr-story-markdown/v1"
id: "025afe1971445afbcaefefc4c98f8355cc19ae0d644a8d29b1281faa11cdd02e"
canonical_url: "https://aidr.today/025afe19?lang=en"
title: "Claude Opus 5.5 Leads First AI Code Merge Test with 52% Score"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-12T19:42:18.000Z"
category: "Models"
topics: ["anthropic","coding","google","llm","devtools"]
source_urls: ["https://huggingnews.com/ai/gemini-4-argon-beats-claude-opus-55-with-779percent-deepswe-score-319baeff","https://marketbrief.now/ai/gemini-4-argon-beats-claude-opus-55-with-779percent-deepswe-score-319baeff","https://x.com/ArtificialAnlys/status/2109703511843979391","https://x.com/cognition/status/2109728065782001869","https://x.com/teortaxesTex/status/2109964464439304562"]
summary: "Artificial Analysis published results for FrontierCode 1.1, a private evaluation created by Cognition to test if AI-generated code is accepted into real-world software repositories. Nine models from six labs scored between 43% and 52%, with Anthropic's Claude Opus 5.5 achieving the highest mark. OpenAI's GPT-6.1 Sol showed the strongest performance for its cost, scoring 49% at $0.81 per task compared to $10.15 for Claude Opus 5.5."
---

# Claude Opus 5\.5 Leads First AI Code Merge Test with 52% Score

> [Open the canonical story](<https://aidr.today/025afe19?lang=en>)

**Published:** 2026-10-12T19:42:18.000Z
**Category:** Models
**Topics:** anthropic, coding, google, llm, devtools

## Summary

Artificial Analysis published results for FrontierCode 1\.1, a private evaluation created by Cognition to test if AI\-generated code is accepted into real\-world software repositories\. Nine models from six labs scored between 43% and 52%, with Anthropic's Claude Opus 5\.5 achieving the highest mark\. OpenAI's GPT\-6\.1 Sol showed the strongest performance for its cost, scoring 49% at $0\.81 per task compared to $10\.15 for Claude Opus 5\.5\.

## Sources

- [Story source](<https://huggingnews.com/ai/gemini-4-argon-beats-claude-opus-55-with-779percent-deepswe-score-319baeff>)
- [Story source](<https://marketbrief.now/ai/gemini-4-argon-beats-claude-opus-55-with-779percent-deepswe-score-319baeff>)
- [Story source](<https://x.com/ArtificialAnlys/status/2109703511843979391>)
- [Supporting source](<https://x.com/cognition/status/2109728065782001869>)
- [Supporting source](<https://x.com/teortaxesTex/status/2109964464439304562>)