🏭 Universal Coding Data Factory Launched
We launched a Universal Coding Data Factory—fully automated, language-agnostic, and Adapter-driven—to continuously turn GitHub repositories into validated training data for any coding task format.
News
📈 Data Factory Training Delivers Gains
In internal mixed-task RL experiments using data from our Universal Coding Data Factory, Qwen3.8-27B improved SWE-bench Verified Pass@1 from 70.2% to a peak of 79.8% and FeatureBench 1.1 Tests Passed from 50.3% to a peak of 60.3%.
📦 FeatureBench Dataset V1.1 Released
We released FeatureBench Dataset V1.1, primarily correcting inconsistencies and omissions in task problem statements.
📊 Lite Leaderboard Expanded
We added lite split evaluation results for frontier models including GPT-5.5, Claude Opus 4.7, DeepSeek-V4, GLM-5.1, Kimi-2.6, Mimo-V2.5-Pro, and more to the leaderboard.
🚀 Fast Split Released
We released the fast split containing 100 instances (a subset of the full split). These instances require no GPU and are optimized for rapid evaluation. On an Intel Xeon Platinum 8457C with 944GB RAM, the average evaluation time per instance using gold patches is 57.2 seconds.
🎁 One-Click Inference Released
We added one-click inference for mainstream agent frameworks, including OpenHands, Claude Code, Codex, Gemini CLI, and mini-swe-agent. All supported agent frameworks can be found here.
🦊 Introducing FeatureBench
FeatureBench is an execution-based benchmark for evaluating agents on end-to-end development of complex real features.