GPT-5.6 officially released: Agent evaluation leads Claude Fable model by 13.1 points

According to Beating monitoring, OpenAI has released the GPT-5.6 series, including the flagship model Sol, the balanced version Terra, and the low-cost version Luna. The new models have launched on ChatGPT, Codex, and API.

GPT-5.6 Sol focuses on performance and efficiency. In the professional Agent evaluation, Agents’ Last Exam, Sol scored 53.6, which is 13.1 points higher than Claude Fable 5. With medium reasoning intensity, it still leads by 11.4 points, with an estimated cost of about one-fourth of the other side.

Programming capabilities have also improved. Sol scored 80 points in the Artificial Analysis coding Agent index, 2.8 points higher than Fable 5, while outputting fewer than half the tokens, taking less than half the time, and costing about one-third less.

GPT-5.6 also adds an ultra mode. By default, it makes 4 Agents work in parallel, using more tokens to deliver stronger results and shorter runtime. API users can also call the multi-Agent beta.

For the API, the input and output prices per 1 million tokens are: Sol $5 and $30, Terra $2.5 and $15, Luna $1 and $6.

View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
Add a comment
Add a comment
No comments
  • Pinned