Judge Accuracy on Ultra-Problem (Target)
61.5AccuracySeed Rubric
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Seed RubricJudge Model=Qwen3-14B2026.02 | 61.5 | 11.3 | |
| Biased Rubric SearchJudge Model=Qwen3-14B2026.02 | 57.6 | 15.4 |
| Method | Links | ||
|---|---|---|---|
| Seed RubricJudge Model=Qwen3-14B2026.02 | 61.5 | 11.3 | |
| Biased Rubric SearchJudge Model=Qwen3-14B2026.02 | 57.6 | 15.4 |