Pair a frontier model with a cheap sidekick to cut coding costs

Artificial Analysis benchmarked Cognition's Devin Fusion, which pairs a frontier model with the cheaper SWE-2 model as a sidekick. The GPT-6 Astra pairing costs 43 percent less and runs 31 percent faster than a Claude Fable 5.1 pairing while scoring close behind it. Read: Artificial Analysis benchmarked Cognition's Devin Fusion, which pairs a frontier model with the cheaper SWE-2 model as a sidekick. The GPT-6 Astra pairing costs 43 percent less and runs 31 percent faster than a Claude Fable 5.1 pairing while scoring close behind it. Read: OpenAI moved GPT-Rosalind, its biological reasoning model, out of research preview into general availability across the API, Codex, and ChatGPT Enterprise, adding Life Sciences plugins for genomic and protein structure work. Read: DeepSeek V4.1 Flash processed 1 trillion tokens in its first 24 hours on OpenRouter, on pace for the largest 48 hour paid model launch yet, with 90 percent of tokens served from cache at about $0.006 per million tokens. Read: Sakana AI launched Fugu Max and Fugu Ultra v2, orchestration systems that route tasks across a large pool of open and specialized models, including NVIDIA Nemotron, claiming benchmark wins over Opus 5 without relying on any single closed model. Read: Simon Willison and Alex Garcia shipped two Datasette security patches after auditing the codebase with Claude Fable 5.1, GPT-5.6, and GPT-6 Astra, then split verification work so one person wrote the failing test and the other implemented each fix. Read: Qwen3.8-27B is now served on Cerebras hardware for fast inference, with Artificial Analysis scoring it near GPT-5.6, DeepSeek V4 Pro, and Claude Sonnet 4.6, though early testers report it underperforms on coding tasks.