Mathematical Reasoning on MathInstruct Scenario 2
83.8AccuracyLaDa
Evaluation results
| Method | Links | ||
|---|---|---|---|
| LaDaSetting=One-shot, Client=LLM2026.02 | 83.8 | 0.4 | |
| LaDaSetting=Zero-shot, Client=LLM2026.02 | 54.2 | 4.7 | |
| LaDaSetting=One-shot, Client=Client 32026.02 | 48.4 | 1.6 | |
| LaDaSetting=One-shot, Client=Client 22026.02 | 45.6 | 1.4 | |
| LaDaSetting=Zero-shot, Client=Client 22026.02 | 38.2 | 0.2 | |
| LaDaSetting=Zero-shot, Client=Client 32026.02 | 32.8 | 3.8 | |
| LaDaSetting=Zero-shot, Client=Client 12026.02 | 24.6 | 0.8 | |
| LaDaSetting=One-shot, Client=Client 12026.02 | 22.2 | 0.4 |