Detection generation on Gold-standard detections
0.578Mean Scoregpt-5
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| gpt-5Tier=medium, Approach=Agentic2026.03 | 0.578 | 0.545 | |
| gpt-5.1Tier=high, Approach=Agentic2026.03 | 0.575 | 0.549 | |
| gpt-5-miniTier=high, Approach=Agentic2026.03 | 0.553 | 0.541 | |
| gpt-5.1Tier=medium, Approach=Agentic2026.03 | 0.547 | 0.52 | |
| gpt-5Tier=high, Approach=Agentic2026.03 | 0.545 | 0.526 |