VibeLifeBench: leaderboard
Personal-assistant tasks that run for weeks in a world that changes underneath them, scored on proactivity and persistence. Deliberately unlike the short self-contained requests in a static environment that most agent evaluations use.
Metric: Average of 3 runs (%). Source: arxiv.org. Saturation forecast: Around 2029. 7 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 5 | 32.5 | #12 |
| 2 | GPT-5.5 | 30.1 | #31 |
| 3 | Claude Opus 4.8 | 27.5 | #37 |
| 4 | Gemini 3.5 Flash | 27.5 | #60 |
| 5 | GLM-5.2 | 25.4 | #73 |
| 6 | Kimi K2.6 | 22.6 | #104 |
| 7 | DeepSeek V4 Pro | 21.1 | #102 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=vibelifebench · How It Works · Data refreshed daily, snapshot 2026-10-20.