Corridor's 9B safety model Argos 1 beats GPT-6 and Claude Opus 5.5

Corridor released Argos 1, a 9B model fine-tuned on Qwen 3.5 using LangSmith agent traces via smithtune, topping a 14-model safety context selection benchmark ahead of GPT-6 Astra and Claude Opus 5.5.

2026-10-22 ~ 2026-10-22 · 3 related posts

• Corridor's 9B fine-tune beats GPT-6 Astra and Claude Opus 5.5 on security context task — LangChain · 2026-10-22
• Corridor's Argos 1: SFT'd Qwen3.5-9B beats GPT-6 and Opus 5.5 on agent security-guidance selection — LangChain · 2026-10-22
• Corridor fine-tunes 9B Argos from LangSmith agent traces, tops its 14-model benchmark — LangChain · 2026-10-22