Harness-Bench: Measuring Harness Effects across Models in Realistic Agent Workflows
Paper • 2605.27922 • Published
Works Mentioning or Using ClawBench
-
-
WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation
Paper • 2605.10912 • Published • 46 -
UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks
Paper • 2607.08768 • Published • 34 -
Auditing Agent Harness Safety
Paper • 2605.14271 • Published • 55 -
NeuroClaw Technical Report
Paper • 2604.24696 • Published • 1 -
VibeSearchBench: Benchmarking Long-horizon Proactive Search in the Wild
Paper • 2605.27882 • Published • 17 -
π-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows
Paper • 2605.14678 • Published • 108 -
MacAgentBench: Benchmarking AI Agents on Real-World macOS Desktop
Paper • 2606.22557 • Published -
Claw-Anything: Benchmarking Always-On Personal Assistants with Broader Access to User's Digital World
Paper • 2605.26086 • Published • 25 -
TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training
Paper • 2607.05804 • Published • 19 -
Mach-Mind-4-Flash Technical Report
Paper • 2607.09375 • Published -
MyPCBench: A Benchmark for Personally Intelligent Computer-Use Agents
Paper • 2606.16748 • Published • 7 -
AcademiClaw: When Students Set Challenges for AI Agents
Paper • 2605.02661 • Published • 17 -
LITMUS: Benchmarking Behavioral Jailbreaks of LLM Agents in Real OS Environments
Paper • 2605.10779 • Published -
On Time, Within Budget: Constraint-Driven Online Resource Allocation for Agentic Workflows
Paper • 2605.06110 • Published • 17