Agent interaction on Agent
100Clean Success (Eager)Llama-3.2-1B-Instruct
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Llama-3.2-1B-InstructExecution Backend=CUDAGraphs, Attack=Attack II2026.05 | 100 | 100 | 37.5 | 68.8 | |
| Llama-3.2-3B-InstructExecution Backend=CUDAGraphs, Attack=Attack II2026.05 | 100 | 100 | 41.2 | 56.2 | |
| Qwen2.5-1.5B-InstructExecution Backend=CUDAGraphs, Attack=Attack II2026.05 | 100 | 100 | 90 | 66.2 | |
| Qwen2.5-3B-InstructExecution Backend=CUDAGraphs, Attack=Attack II2026.05 | 100 | 100 | 65 | 60 |