OSWorld 2.0 (offline, 2026-08-08, partial)

Updated Sep 5, 2026·0 views

Problem Count: —
Institution: OpenAI
Category: AI Agent - Tool Use
Metrics: Score (%)
Language: English
Difficulty: —

Overview

v2026.08.08 offline subset, partial score; not online/full-set or strict success.

Related resources

Official Website

Latest OSWorld 2.0 (offline, 2026-08-08, partial) model rankings and full benchmark leaderboard

Browse the latest scores, model modes, release dates, and parameter sizes for OSWorld 2.0 (offline, 2026-08-08, partial).

Source: DataLearnerAI

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Model Mode Legend

License:

Origin:

Model release cutoff:

Rank	Model				License
	GPT-6 Astra unknown	72.60	2026-09-03	Unknown	Closed
	GPT-5.6 Sol unknown	65.70	2026-06-26	Unknown	Closed

Latest OSWorld 2.0 (offline, 2026-08-08, partial) model rankings and full benchmark leaderboard

OSWorld 2.0 (offline, 2026-08-08, partial) Rank