Skip to content
Trending storyDeveloping

Interaction Bench 0.1 Preview benchmark ranks GPT-6 Astra first at 34.1%

1 article1 sourcesince Oct 29Last article 5h ago ·

Overview

AISummary of 1 article

Arvin Xu (空谷) introduces Interaction Bench 0.1 Preview, a benchmark that tests AI agents on 44 tasks drawn from 25 real open-source apps.

Agents receive only the user's goal, not the bug. In the preview results Xu posted, GPT-6 Astra scores 34.1%, Claude Opus 5.5 scores 27.3%, and the other models score between 4.5% and 15.9%.

Written by AI from the articles below · updated Oct 29, 6:05 PM ET

Check the sources:

Latest developmentOct 29, 2:17 PM ET
Interaction Bench 0.1 Preview ranks GPT-6 Astra first at 34.1%

Article timeline

The articles in this story. Times are ET.

Oct 29
  1. 空谷 Arvin XuX
    Interaction Bench 0.1 Preview ranks GPT-6 Astra first at 34.1%

    AIInteraction Bench 0.1 Preview is a new benchmark that tests AI agents on 44 tasks drawn from 25 real open-source apps, with agents given only the user's goal and never the bug. GPT-6 Astra leads at 34.1%, followed by Claude Opus 5.5 at 27.3%, while the other models score between 4.5% and 15.9%.

    Image from @arvin17x's post

Heat Trend

Not enough continuous observations to show a trend yet.