Question 1

What is OSWorld 2.1 (offline)?

Accepted Answer

: Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Version 2.1, in its offline setting. Scores are not comparable with version 2.0. Higher is better.
: Claude Haiku 5.5 by Anthropic holds the best OSWorld 2.1 (offline) result among tracked models, at 72.4% (released Oct 7 2026). Higher scores are better on this benchmark.
: 1. Claude Haiku 5.5 (Anthropic) — 72.4%; 2. Claude Haiku 4.5 (Anthropic) — 15.7%.
: 2 tracked models have a published OSWorld 2.1 (offline) score. Scores are collected from published lab reports and benchmark sources, with recorded sources credited alongside the results. We do not re-run the evaluations.

Question 2

Which AI model scores highest on OSWorld 2.1 (offline)?

Accepted Answer

Claude Haiku 5.5 by Anthropic holds the best OSWorld 2.1 (offline) result among tracked models, at 72.4% (released Oct 7 2026). Higher scores are better on this benchmark.

Question 3

What are the top 2 models on OSWorld 2.1 (offline)?

Accepted Answer

1. Claude Haiku 5.5 (Anthropic) — 72.4%; 2. Claude Haiku 4.5 (Anthropic) — 15.7%.

Question 4

How many models have a published OSWorld 2.1 (offline) score?

Accepted Answer

2 tracked models have a published OSWorld 2.1 (offline) score. Scores are collected from published lab reports and benchmark sources, with recorded sources credited alongside the results. We do not re-run the evaluations.

OSWorld 2.1 (offline)

Rankings

OSWorld 2.1 (offline) — frequently asked questions