# ClawBench: Can AI Agents Complete Everyday Online Tasks?

arXiv: https://arxiv.org/abs/2604.08523 · HTML: https://mlsanity.com/paper/2604.08523/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 35 references that are in the map.
- First posted on arXiv 9 Apr 2026.

## Builds on (most cited first, 26 of 26)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [GLM-5: from Vibe Coding to Agentic Engineering](https://mlsanity.com/paper/2602.15763/) (2026)
- [GPT-4V(ision) is a Generalist Web Agent, if Grounded](https://mlsanity.com/paper/2401.01614/) (2024)
- [Kimi K2.5: Visual Agentic Intelligence](https://mlsanity.com/paper/2602.02276/) (2026)
- [WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models](https://mlsanity.com/paper/2401.13919/) (2024)
- [A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis](https://mlsanity.com/paper/2307.12856/) (2023)
- [TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks](https://mlsanity.com/paper/2412.14161/) (2024)
- [BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent](https://mlsanity.com/paper/2508.06600/) (2025)
- [An Illusion of Progress? Assessing the Current State of Web Agents](https://mlsanity.com/paper/2504.01382/) (2025)
- [AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?](https://mlsanity.com/paper/2407.15711/) (2024)
- [WebCanvas: Benchmarking Web Agents in Online Environments](https://mlsanity.com/paper/2406.12373/) (2024)
- [MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers](https://mlsanity.com/paper/2508.20453/) (2025)
- [Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents](https://mlsanity.com/paper/2604.06132/) (2026)
- [REAL: Benchmarking Autonomous Agents on Deterministic Simulations of Real Websites](https://mlsanity.com/paper/2504.11543/) (2025)
- [BrowserAgent: Building Web Agents with Human-Inspired Web Browsing Actions](https://mlsanity.com/paper/2510.10666/) (2025)
- [Investigating the Impact of Dark Patterns on LLM-Based Web Agents](https://mlsanity.com/paper/2510.18113/) (2025)
- [EconWebArena: Benchmarking Autonomous Agents on Economic Tasks in Realistic Web Environments](https://mlsanity.com/paper/2506.08136/) (2025)
- [SWE-QA-Pro: A Representative Benchmark and Scalable Training Recipe for Repository-Level Code Understanding](https://mlsanity.com/paper/2603.16124/) (2026)
- [SWE-Next: Scalable Real-World Software Engineering Tasks for Agents](https://mlsanity.com/paper/2603.20691/) (2026)
- [SwingArena: Competitive Programming Arena for Long-context GitHub Issue Solving](https://mlsanity.com/paper/2505.23932/) (2025)
- [Dr. Bench: A Multidimensional Evaluation for Deep Research Agents, from Answers to Reports](https://mlsanity.com/paper/2510.02190/) (2025)

## Built on by (most cited first, 30 of 33)

- [Harness-Bench: Measuring Harness Effects across Models in Realistic Agent Workflows](https://mlsanity.com/paper/2605.27922/) (2026)
- [WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation](https://mlsanity.com/paper/2605.10912/) (2026)
- [TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training](https://mlsanity.com/paper/2607.05804/) (2026)
- [Auditing Agent Harness Safety](https://mlsanity.com/paper/2605.14271/) (2026)
- [PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents](https://mlsanity.com/paper/2608.04003/) (2026)
- [Stealing Reasoning Traces from Proprietary LLM APIs](https://mlsanity.com/paper/2608.09867/) (2026)
- [ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement](https://mlsanity.com/paper/2609.14857/) (2026)
- [MyPCBench: A Benchmark for Personally Intelligent Computer-Use Agents](https://mlsanity.com/paper/2606.16748/) (2026)
- [π-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows](https://mlsanity.com/paper/2605.14678/) (2026)
- [From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI](https://mlsanity.com/paper/2606.14502/) (2026)
- [LITMUS: Benchmarking Behavioral Jailbreaks of LLM Agents in Real OS Environments](https://mlsanity.com/paper/2605.10779/) (2026)
- [NeuroClaw Technical Report](https://mlsanity.com/paper/2604.24696/) (2026)
- [Mach-Mind-4-Flash Technical Report](https://mlsanity.com/paper/2607.09375/) (2026)
- [On Time, Within Budget: Constraint-Driven Online Resource Allocation for Agentic Workflows](https://mlsanity.com/paper/2605.06110/) (2026)
- [Redundant or Necessary? A Benchmark for Detecting Redundant Steps in Agent Trajectories](https://mlsanity.com/paper/2605.29893/) (2026)
- [UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks](https://mlsanity.com/paper/2607.08768/) (2026)
- [MedClaw: Heuristic Agent Harness for Long-Horizon Surgical Video Reasoning](https://mlsanity.com/paper/2608.14015/) (2026)
- [Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context](https://mlsanity.com/paper/2605.13831/) (2026)
- [Claw-Anything: Benchmarking Always-On Personal Assistants with Broader Access to User's Digital World](https://mlsanity.com/paper/2605.26086/) (2026)
- [SecRespond: Benchmarking AI Agents for Real-World Post-Compromise Incident Response](https://mlsanity.com/paper/2607.26791/) (2026)
- [ClawTrack: Towards Trace-Level Evaluation and Improvement of Real-World Autonomous Agents](https://mlsanity.com/paper/2607.28037/) (2026)
- [DuMateBench: Evaluating Autonomous Agents in Complex Real-World Workflows](https://mlsanity.com/paper/2608.26546/) (2026)
- [AcademiClaw: When Students Set Challenges for AI Agents](https://mlsanity.com/paper/2605.02661/) (2026)
- [Securing Computer-Use Agents: A Unified Architecture-Lifecycle Framework for Deployment-Grounded Reliability](https://mlsanity.com/paper/2605.07110/) (2026)
- [Can a Single Message Paralyze the AI Infrastructure? The Rise of AbO-DDoS Attacks through Targeted Mobius Injection](https://mlsanity.com/paper/2605.11442/) (2026)
- [DAREBench: Deployment-Aware and Reliable Evaluation of Models as Agents](https://mlsanity.com/paper/2609.06059/) (2026)
- [Trust and Task Completion in the World of Consumer AI Agents](https://mlsanity.com/paper/2609.33017/) (2026)
- [cua-speedrun: Standardized Benchmarking of the Speed of Computer-Use Agents](https://mlsanity.com/paper/2609.40284/) (2026)
- [Deny Without Disabling: Authorization-Paired Evaluation and Control for Multi-Agent Systems](https://mlsanity.com/paper/2610.00371/) (2026)
- [ClawLoop: Self-Improving Agents via Harness-Native Training Loop](https://mlsanity.com/paper/2610.14118/) (2026)

## Abstract (arXiv)

AI agents may be able to assist with emails and documents, but can they reliably complete everyday online workflows on real websites? 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 comprising 153 everyday online tasks that people need to accomplish regularly in their lives and work, spanning 144 platforms across 15 categories, from completing purchases and booking appointments to submitting job applications. These tasks require 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 interaction challenges of real-world web environments. An interception layer captures and blocks the final submission request, ensuring safe evaluation without real-world side effects. Our evaluations of 8 frontier models show that both proprietary and open-source models complete only a small portion of these tasks. For example, Claude Sonnet 4.6 achieves only 33.3%, which exposes gaps in current AI agents. Progress on ClawBench brings us closer to AI agents that can function as general-purpose assistants.