# BAAI releases AREX-2, a 27B model built on Qwen3.8-27B

> Original title: Can a 27B model push the Pareto frontier of autonomous research and beat 1T–2.8T giants?

- Source: BAAI
- Published: 2026-10-27T13:12:00.000Z
- Bad Influence: https://badinfluence.news/items/pkj481cyoiippnpy5zrp6vkx3
- Original: https://x.com/BAAIBeijing/status/2115069000098906244

## Summary

BAAI, with USTC and RUC, releases AREX-2, a 27B model built on Qwen3.8-27B. The post says it scores 81.8 on MLE-bench Lite and sets new ≤40B state-of-the-art results on BrowseComp (84.0) and HLE (52.6). The benchmark chart also reports 93.8 on DeepSearchQA and 92.2 on GAIA.

## Post

Can a 27B model push the Pareto frontier of autonomous research and beat 1T–2.8T giants?

Meet AREX-2 (27B), spearheaded by BAAI in collaboration with USTC and RUC (built on Qwen3.8-27B). Turning Recursive Self-Improvement (RSI) into a practical test-time scaling paradigm, we pinpoint two keys to self-evolution: Deep Reflection & Long-Horizon Execution. By reinforcing algorithmic optimization tasks, AREX-2 emerges with exceptional deep reflection and long-horizon execution capabilities—significantly boosting its performance oncomplex coding and deep research to top MLE-bench Lite (81.8) and set new ≤40B SOTA on BrowseComp (84.0) & HLE (52.6)👇

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHVoC9hgb0AA0lgW.jpg&mode=thumb&exp=1793404800&sig=7db71cc5db8c2da5)