Mathematical Reasoning on MathInstruct Scenario 3
83.2AccuracyLaDa
Evaluation results
| Method | Links | ||
|---|---|---|---|
| LaDaSetting=One-shot, Client=Client 32026.02 | 83.2 | 1.2 | |
| LaDaSetting=One-shot, Client=Client 22026.02 | 70.4 | 0.8 | |
| LaDaSetting=Zero-shot, Client=Client 32026.02 | 64.4 | 13.8 | |
| LaDaSetting=One-shot, Client=LLM2026.02 | 49.8 | 3.8 | |
| LaDaSetting=One-shot, Client=Client 12026.02 | 44.8 | 1.4 | |
| LaDaSetting=Zero-shot, Client=Client 22026.02 | 43 | 1 | |
| LaDaSetting=Zero-shot, Client=Client 12026.02 | 35 | 2.2 | |
| LaDaSetting=Zero-shot, Client=LLM2026.02 | 27.8 | 1.1 |