Dense label evaluation via binary claim accuracy diagnostic on KataGo
81.1Binary Claim Accuracyverifier-coupled reasoning
Evaluation Results
| Method | Links | |
|---|---|---|
| verifier-coupled reasoningCondition=Trained2026.06 | 81.1 | |
| ControlCondition=Control2026.06 | 25.1 |
| Method | Links | |
|---|---|---|
| verifier-coupled reasoningCondition=Trained2026.06 | 81.1 | |
| ControlCondition=Control2026.06 | 25.1 |