Skip to content
Trending storyDeveloping

BAAI releases AREX-2 27B model with top MLE-bench Lite and BrowseComp scores

1 article1 sourcesince Oct 27Last article

Overview

AISummary of 1 article

BAAI, with USTC and RUC, releases AREX-2, a 27B model built on Qwen3.8-27B. According to BAAI's X post, AREX-2 scores 81.8 on MLE-bench Lite and sets new state-of-the-art results for models of 40B parameters or fewer on BrowseComp (84.0) and HLE (52.6).

The same post's benchmark chart also reports 93.8 on DeepSearchQA and 92.2 on GAIA. BAAI attributes the gains to reinforcement learning on algorithmic optimization tasks, which it says improves deep reflection and long-horizon execution on complex coding and deep research.

Written by AI from the articles below · updated Oct 27, 9:26 AM ET

Check the sources:

Latest developmentOct 27, 9:12 AM ET
BAAI releases AREX-2, a 27B model built on Qwen3.8-27B

Article timeline

The articles in this story. Times are ET.

Oct 27
  1. BAAIOfficial
    BAAI releases AREX-2, a 27B model built on Qwen3.8-27B

    AIBAAI, 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.

    Image from @BAAIBeijing's post

Heat Trend

Current comparable heat
6
Peak comparable heat
10Oct 27, 10:00 AM ET
Change in past 24 hours
–

The trend compares only continuously observed participants, so its scope may be smaller than the current heat total. Hover or tap for hourly heat; use arrow keys with a keyboard.