Mathematical Reasoning on MathInstruct Scenario 1
68.4AccuracyLaDa
Evaluation results
| Method | Links | ||
|---|---|---|---|
| LaDaSetting=One-shot, Client=Client 22026.02 | 68.4 | 9.6 | |
| LaDaScenario=Scenario 1, Evaluation Protocol=Zero-shot setting, Client Identifier=Client 22026.02 | 68.4 | — | |
| WASPSetting=One-shot, Client=Client 22026.02 | 58.8 | — | |
| FedMKTSetting=One-shot, Client=Client 22026.02 | 58.2 | — | |
| rStarScenario=Scenario 1, Evaluation Protocol=Zero-shot setting, Client Identifier=Client 22026.02 | 54.4 | — | |
| LaDaSetting=One-shot, Client=Client 32026.02 | 52.2 | 1 | |
| LaDaScenario=Scenario 1, Evaluation Protocol=Zero-shot setting, Client Identifier=Client 32026.02 | 52.2 | — | |
| rStarScenario=Scenario 1, Evaluation Protocol=Zero-shot setting, Client Identifier=Client 32026.02 | 51.6 | — | |
| WASPSetting=One-shot, Client=Client 32026.02 | 51.2 | — | |
| LaDaSetting=Zero-shot, Client=Client 22026.02 | 48.6 | 2.4 | |
| LaDaSetting=Zero-shot, Client=Client 32026.02 | 47 | 0.6 | |
| SOCRATIC COTScenario=Scenario 1, Evaluation Protocol=Zero-shot setting, Client Identifier=Client 32026.02 | 47 | — | |
| WASPSetting=Zero-shot, Client=Client 32026.02 | 46.4 | — | |
| FedMKTSetting=Zero-shot, Client=Client 22026.02 | 46.2 | — | |
| FedKDSetting=Zero-shot, Client=Client 22026.02 | 46 | — | |
| FedKDSetting=Zero-shot, Client=Client 32026.02 | 46 | — | |
| LaDaSetting=One-shot, Client=LLM2026.02 | 45.9 | 2.6 | |
| LaDaScenario=Scenario 1, Evaluation Protocol=Zero-shot setting, Client Identifier=LLM2026.02 | 45.9 | — | |
| SOCRATIC COTScenario=Scenario 1, Evaluation Protocol=Zero-shot setting, Client Identifier=Client 22026.02 | 45.4 | — | |
| WASPSetting=Zero-shot, Client=Client 22026.02 | 44 | — | |
| StandaloneSetting=One-shot, Client=Client 32026.02 | 43.5 | — | |
| StandaloneSetting=Zero-shot, Client=Client 32026.02 | 43.4 | — | |
| FedKDSetting=One-shot, Client=Client 32026.02 | 43.3 | — | |
| FedKDSetting=One-shot, Client=LLM2026.02 | 43.3 | — | |
| WASPSetting=One-shot, Client=LLM2026.02 | 43.3 | — | |
| SFTScenario=Scenario 1, Evaluation Protocol=Zero-shot setting, Client Identifier=Client 32026.02 | 43.2 | — | |
| FedMKTSetting=One-shot, Client=LLM2026.02 | 43.1 | — | |
| StandaloneSetting=One-shot, Client=LLM2026.02 | 42.7 | — | |
| SFTScenario=Scenario 1, Evaluation Protocol=Zero-shot setting, Client Identifier=Client 22026.02 | 41.8 | — | |
| StandaloneSetting=Zero-shot, Client=Client 22026.02 | 41.2 | — | |
| StandaloneSetting=One-shot, Client=Client 22026.02 | 41 | — | |
| FedMKTSetting=One-shot, Client=Client 32026.02 | 38.6 | — | |
| FedMKTSetting=Zero-shot, Client=Client 32026.02 | 37.6 | — | |
| FedKDSetting=One-shot, Client=Client 22026.02 | 30.8 | — | |
| LaDaSetting=Zero-shot, Client=LLM2026.02 | 30.6 | 1.2 | |
| WASPSetting=Zero-shot, Client=LLM2026.02 | 29.4 | — | |
| FedMKTSetting=Zero-shot, Client=LLM2026.02 | 28.5 | — | |
| FedKDSetting=Zero-shot, Client=LLM2026.02 | 27.5 | — | |
| LaDaSetting=Zero-shot, Client=Client 12026.02 | 27.2 | 0.8 | |
| WASPSetting=Zero-shot, Client=Client 12026.02 | 26.4 | — | |
| StandaloneSetting=Zero-shot, Client=LLM2026.02 | 26.2 | — | |
| FedMKTSetting=Zero-shot, Client=Client 12026.02 | 26 | — | |
| LaDaSetting=One-shot, Client=Client 12026.02 | 25.8 | 3 | |
| LaDaScenario=Scenario 1, Evaluation Protocol=Zero-shot setting, Client Identifier=Client 12026.02 | 25.8 | — | |
| FedKDSetting=Zero-shot, Client=Client 12026.02 | 24 | — | |
| FedMKTSetting=One-shot, Client=Client 12026.02 | 22.8 | — | |
| rStarScenario=Scenario 1, Evaluation Protocol=Zero-shot setting, Client Identifier=Client 12026.02 | 22.6 | — | |
| StandaloneSetting=One-shot, Client=Client 12026.02 | 22 | — | |
| SFTScenario=Scenario 1, Evaluation Protocol=Zero-shot setting, Client Identifier=Client 12026.02 | 22 | — | |
| WASPSetting=One-shot, Client=Client 12026.02 | 21.4 | — | |
| SOCRATIC COTScenario=Scenario 1, Evaluation Protocol=Zero-shot setting, Client Identifier=Client 12026.02 | 21.4 | — | |
| FedKDSetting=One-shot, Client=Client 12026.02 | 19.8 | — | |
| StandaloneSetting=Zero-shot, Client=Client 12026.02 | 17.8 | — |