Prompt Injection Robustness on Internal PI Benchmark
100RobustnessGPT-5-Mini-R
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-5-Mini-RModel=GPT-5-Mini-R2026.03 | 100 | |
| GPT-5-MiniModel=GPT-5-Mini2026.03 | 44 |
Loading the SOTA2 catalog…
| Method | Links | |
|---|---|---|
| GPT-5-Mini-RModel=GPT-5-Mini-R2026.03 | 100 | |
| GPT-5-MiniModel=GPT-5-Mini2026.03 | 44 |