Skip to content
AI News HubLIVE
More
Summary only

Ant Bailing Ring-2.6-1T Open Source with Enhanced Agent Execution Capabilities

Ant Group's Bailing releases open-source reasoning model Ring-2.6-1T, featuring on-demand reasoning with adjustable effort, scoring 95.83 on AIME 26, and trained with asynchronous reinforcement learning.

Source量子位Author: 量子位的朋友们
Ant Bailing Ring-2.6-1T Open Source with Enhanced Agent Execution Capabilities
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions

Summary only

Under the source content permission, this page provides an editorial summary, key points, and a link to the original article.

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Ring-2.6-1T open source, supports high and xhigh reasoning effort
  • High mode optimizes agent workflows; xhigh mode for challenging tasks
  • AIME 26 score 95.83, GPQA Diamond 88.27
  • Asynchronous RL training with 'popsicle algorithm' for stability

Highlights and analysis are generated automatically and may contain errors. Check the original source.