Evaluation Awareness Detection on Apollo Evaluation Traces (Overall)
0.218Overall Rategpt-5-thinking
Evaluation Results
| Method | Links | |
|---|---|---|
| gpt-5-thinkingEvaluation awareness definition=Broad2025.12 | 0.218 | |
| gpt-5-thinkingEvaluation awareness definition=Strict2025.12 | 0.129 |