Together AI· Inference platformResearch paper

CoderForge-Preview: SOTA open dataset for training efficient coding agents

Together AI releases CoderForge-Preview, the largest open dataset of coding agent trajectories (258k trajectories, 128K context length). Fine-tuning Qwen-3 32B on this dataset achieves 59.4% pass@1 on SWE-Bench Verified, a 23.0% improvement over the base model and ranking #1 among open-data models in the ≤32B parameter range.

From the source

We release CoderForge-Preview - the largest open test-verified coding agent dataset. By leveraging it to fine-tune Qwen-3 32B, we boost SWE-Bench Verified performance 23.0% above the base model reaching 59.4%, ranking #1 among open-data models in the ≤32B parameter range.

together.ai

Announced

25 Feb 2026 00:00 UTC

Detected

03 Aug 2026 21:12 UTC (+159d after)