Mathematical Reasoning on BeyondAIME (Turn 1, Turn 2, Δ)
2Turn 1 ScoreUntrained baseline
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Untrained baselineBase Model=Qwen3-1.7B2026.05 | 2 | 2 | 0 | |
| Bi-NACBase Model=Qwen3-1.7B2026.05 | 2 | 4 | 2 |
| Method | Links | |||
|---|---|---|---|---|
| Untrained baselineBase Model=Qwen3-1.7B2026.05 | 2 | 2 | 0 | |
| Bi-NACBase Model=Qwen3-1.7B2026.05 | 2 | 4 | 2 |