AgingBench: leaderboard
Long-lived AI agents are increasingly deployed as persistent operational systems, yet they are still evaluated like freshly initialized models. Day-one benchmarks miss a basic systems question: how long does an agent remain reliable after deployment? Even when model weights are frozen, an agent's effective state keeps changing as it compresses interaction history, retrieves from a growing memory s
Metric: S1 kw_m HL (self-reported). Source: benchmarklist.com. Saturation forecast: Around June 2027. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3 14B | 7.9 | #537 |
| 2 | GPT-4o | 7.6 | #343 |
| 3 | Gemma 4 31B | 7.4 | #200 |
| 4 | Qwen 3 8B | 6.2 | #674 |
| 5 | Llama 3.1 8B | 5.8 | #1151 |
| 6 | GPT-OSS-120B | 5.4 | #341 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=agingbench · How It Works · Data refreshed daily, snapshot 2026-10-20.