OSWorld Extended

OSWorld is a scalable, real computer environment benchmark for evaluating multimodal agents on open-ended tasks across Ubuntu, Windows, and macOS. It comprises 369 computer tasks involving real web and desktop applications, OS file I/O, and multi-application workflows. The benchmark evaluates agents' ability to interact with computer interfaces using screenshots and actions in realistic computing environments.

Claude 3.5 Sonnet from Anthropic currently leads the OSWorld Extended leaderboard with a score of 0.220 across 1 evaluated AI models.

Paper

AnthropicClaude 3.5 Sonnet leads with 22.0%.

Progress Over Time

Interactive timeline showing model performance evolution on OSWorld Extended

State-of-the-art frontier
Open
Proprietary

OSWorld Extended Leaderboard

1 models
ContextCostLicense
1
Notice missing or incorrect data?

FAQ

Common questions about OSWorld Extended.

What is the OSWorld Extended benchmark?

OSWorld is a scalable, real computer environment benchmark for evaluating multimodal agents on open-ended tasks across Ubuntu, Windows, and macOS. It comprises 369 computer tasks involving real web and desktop applications, OS file I/O, and multi-application workflows. The benchmark evaluates agents' ability to interact with computer interfaces using screenshots and actions in realistic computing environments.

What is the OSWorld Extended leaderboard?

The OSWorld Extended leaderboard ranks 1 AI models based on their performance on this benchmark. Currently, Claude 3.5 Sonnet by Anthropic leads with a score of 0.220. The average score across all models is 0.220.

What is the highest OSWorld Extended score?

The highest OSWorld Extended score is 0.220, achieved by Claude 3.5 Sonnet from Anthropic.

How many models are evaluated on OSWorld Extended?

1 models have been evaluated on the OSWorld Extended benchmark, with 0 verified results and 1 self-reported results.

Where can I find the OSWorld Extended paper?

The OSWorld Extended paper is available at https://arxiv.org/abs/2404.07972. The paper details the methodology, dataset construction, and evaluation criteria.

What categories does OSWorld Extended cover?

OSWorld Extended is categorized under agents, general, multimodal, and reasoning. The benchmark evaluates multimodal models.

More evaluations to explore

Related benchmarks in the same category

View all agents
GPQA

A challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry. Questions are Google-proof and extremely difficult, with PhD experts reaching 65% accuracy.

general
214 models
MMLU-Pro

A more robust and challenging multi-task language understanding benchmark that extends MMLU by expanding multiple-choice options from 4 to 10, eliminating trivial questions, and focusing on reasoning-intensive tasks. Features over 12,000 curated questions across 14 domains and causes a 16-33% accuracy drop compared to original MMLU.

general
119 models
AIME 2025

All 30 problems from the 2025 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999. Used as an AI benchmark to evaluate large language models' ability to solve complex mathematical problems requiring multi-step logical deductions and structured symbolic reasoning.

reasoning
109 models
MMLU

Massive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains

general
99 models
SWE-Bench Verified

A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.

reasoning
90 models
Humanity's Last Exam

Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions

reasoningmultimodal
75 models