Allen AI's SERA brings open coding agents to private repos for as little as $400 in training costs

AI research institute Allen AI has released SERA, a family of open-source coding agents designed for easy adaptation to private code bases. The top model, SERA-32B, solves up to 54.2 percent of problems in the SWE-Bench-Test Verified coding benchmark (64K context), outperforming comparable open-source models.

According to AI2, training takes just 40 GPU days and costs between $400 to match previous open-source results and $12,000 for performance on par with leading industry models. This makes training on proprietary code data realistic even for small teams. SERA uses a simplified training method called "Soft-verified Generation" that doesn't require perfectly correct code examples. Technical details can be found in the blog.

The models work with Claude Code and can be launched with just two lines of code, according to Allen AI. All models, code, and instructions are available on Hugging Face under the Apache 2.0 license.