AgentBoard — leaderboard

AgentBoard: Evaluates autonomous agent performance on multi-step tasks requiring planning, state tracking, tool use, and recovery.

Metric: Progress Rate (self-reported). Source: benchmarklist.com. Status: saturation imminent. 13 models tracked.

Top models

#ModelScore
1GPT-470
2Claude 248.9
3GPT-3.5 Turbo41.4
4text-davinci-00337.2
5Mistral 7B24.6
6Llama 2 70B23.8
7Llama 2 13B18.9

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