Arithmetic Reasoning on Average Arithmetic Reasoning Tasks
84.3AccuracyStand
Evaluation Results
| Method | Links | |
|---|---|---|
| StandPerturbation=No Dert.2025.06 | 84.3 | |
| RoPPerturbation=SC2025.06 | 82.3 | |
| RoPPerturbation=EC2025.06 | 82.2 | |
| RoPPerturbation=HW2025.06 | 81.7 | |
| CoTPerturbation=SC2025.06 | 80.8 | |
| CoTPerturbation=EC2025.06 | 80.2 | |
| RoPPerturbation=WOO2025.06 | 80.2 | |
| CoTPerturbation=WOO2025.06 | 79.9 | |
| APEPerturbation=WOO2025.06 | 79.4 | |
| PromptAgentPerturbation=EC2025.06 | 79.3 | |
| CoTPerturbation=HW2025.06 | 79 | |
| StandPerturbation=WOO2025.06 | 78.4 | |
| APEPerturbation=SC2025.06 | 78.3 | |
| StandPerturbation=EC2025.06 | 77.5 | |
| PromptAgentPerturbation=WOO2025.06 | 77.2 | |
| APEPerturbation=HW2025.06 | 76.9 | |
| APEPerturbation=EC2025.06 | 76.7 | |
| StandPerturbation=SC2025.06 | 76 | |
| PromptAgentPerturbation=HW2025.06 | 75.7 | |
| RoPPerturbation=UIC2025.06 | 74 | |
| StandPerturbation=HW2025.06 | 72.2 | |
| PromptAgentPerturbation=SC2025.06 | 71.2 | |
| APEPerturbation=UIC2025.06 | 62.4 | |
| StandPerturbation=UIC2025.06 | 58.9 | |
| CoTPerturbation=UIC2025.06 | 58.4 | |
| PromptAgentPerturbation=UIC2025.06 | 52 |