AgentRewardBench — leaderboard

Benchmark for evaluating reward models and judge systems on agent trajectories from AssistantBench, VisualWebArena, WebArena, WorkArena, and WorkArena++.

Source: agent-reward-bench.github.io.

Interactive version: theaggregate.ai/benchmark?slug=agentrewardbench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.