ATRBench: leaderboard
A long-lived LLM agent, such as OpenClaw, earns its value by acting on a user's preferences and constraints across sessions, not just the current request. Yet today's agents keep what a user volunteers but rarely ask for what stays unspoken, leaving a proactivity gap in long-lived LLM agents: an agent cannot act on a preference it never obtained. As users delegate more of their affairs to agents,
Metric: TSAcc Default (%) (self-reported). Source: benchmarklist.com. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | DeepSeek V4 Flash | 23.7 | #137 |
| 2 | Claude Opus 4.7 | 22.2 | #49 |
| 3 | MiniMax-M2.7 | 20.4 | #258 |
| 4 | Qwen 3.6 Plus | 20.3 | #120 |
| 5 | Gemini 3.1 Pro (Preview) | 20.1 | #58 |
| 6 | DeepSeek V4 Pro | 20 | #102 |
| 7 | GPT-5.4 | 15 | #79 |
Interactive version: theaggregate.ai/benchmark?slug=atrbench · How It Works · Data refreshed daily, snapshot 2026-10-20.