Arena-Hard

'Arena-Hard' is a benchmark used to evaluate the performance of AI agents in instruction-following tasks.

Papers using Arena-Hard (3)

MMoA: An AI-Agent framework with recurrence for Memoried Mixure-of-Agent2026P3: Prompts Promote Prompting2025Multi-Agent Sampling: Scaling Inference Compute for Data Synthesis with Tree Search-Based Agentic Collaboration2024