.@corridor used smithtune’s trace-based workflow to build the training data for Argos, a fine-tuned 9B model that scores the highest of the 14 models they tested on their security context benchmark.
🧵 Full thread ⤵️
Corridor's Argos 9B security model tops 14 models on context benchmark
AICorridor built Argos, a fine-tuned 9B model, using smithtune's trace-based workflow to create its training data. Argos scored highest of the 14 models Corridor tested on its security context benchmark.
@LangChain
Introducing corridor-argos-1, Corridor’s first security model. A Qwen 3.5 9B fine-tune that outperforms frontier models including GPT-6 Astra and Claude Opus 5.5 on security context selection, with the lowest time to first token of the 14 models we tested. Thread 🧵
Source details
LangChain · x.comPublished
Original title: .@corridor used smithtune’s trace-based workflow to build the training data for Argos, a fine-tuned 9B model that scores the highest of t...