Do Agents Know What They Can't Do? Evaluating — leaderboard
Metric: Avg. (self-reported). Source: benchmarklist.com. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 | 61.2 |
| 2 | GPT-OSS-120B | 60.7 |
| 3 | Qwen 3.5 397B A17B | 58.2 |
| 4 | Qwen 3.5 27B | 56.7 |
| 5 | DeepSeek V4 Pro | 54.8 |
| 6 | DeepSeek V4 Flash | 52.9 |
| 7 | Qwen 3.5 122B A10B | 52.3 |
| 8 | Qwen 3.5 35B A3B | 52.3 |
| 9 | Qwen 3.5 9B | 47.2 |
Interactive version: theaggregate.ai/benchmark?slug=do-agents-know-what-they-can-t-do-evaluating · How the rankings work · Data refreshed daily, snapshot 2026-07-22.