ClawBench: Can AI Agents Complete Everyday Online Tasks?

TL;DR

ClawBench is a new evaluation framework for AI agents to perform 153 real-world online tasks across diverse platforms, highlighting current models' limited capabilities in complex web interactions.

Contribution

Introduces ClawBench, a comprehensive, real-world web task benchmark that challenges AI agents with dynamic, multi-step online activities on live websites.

Findings

Current AI models complete only a small portion of tasks, e.g., 33.3% by Claude Sonnet 4.6.

ClawBench captures real-world web interactions safely without side effects.

The benchmark covers diverse categories and complex multi-step workflows.

Abstract

AI agents may be able to automate your inbox, but can they automate other routine aspects of your life? Everyday online tasks offer a realistic yet unsolved testbed for evaluating the next generation of AI agents. To this end, we introduce ClawBench, an evaluation framework of 153 simple tasks that people need to accomplish regularly in their lives and work, spanning 144 live platforms across 15 categories, from completing purchases and booking appointments to submitting job applications. These tasks require demanding capabilities beyond existing benchmarks, such as obtaining relevant information from user-provided documents, navigating multi-step workflows across diverse platforms, and write-heavy operations like filling in many detailed forms correctly. Unlike existing benchmarks that evaluate agents in offline sandboxes with static pages, ClawBench operates on production websites, preserving the full complexity, dynamic nature, and challenges of real-world web interaction. A lightweight interception layer captures and blocks only the final submission request, ensuring safe evaluation without real-world side effects. Our evaluations of 7 frontier models show that both proprietary and open-source models can complete only a small portion of these tasks. For example, Claude Sonnet 4.6 achieves only 33.3%. Progress on ClawBench brings us closer to AI agents that can function as reliable general-purpose assistants.