Mathematical Reasoning on MATH (test) (Sub-category Scores)
94Algebra AccuracySID-v
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| SID-vModel=GPT-OSS-20B2025.10 | 94 | 92 | 79 | 65 | 87 | 91 | 62 | |
| SID-cModel=GPT-OSS-20B2025.10 | 94 | 92 | 80 | 62 | 87 | 91 | 61 | |
| DMADModel=GPT-OSS-20B2025.10 | 91 | 90 | 73 | 51 | 66 | 89 | 47 | |
| COTModel=GPT-OSS-20B2025.10 | 85 | 81 | 56 | 36 | 70 | 84 | 44 | |
| IOModel=GPT-OSS-20B2025.10 | 85 | 81 | 60 | 40 | 74 | 87 | 42 | |
| Self-ContrastModel=GPT-OSS-20B2025.10 | 84 | 75 | 65 | 36 | 67 | 88 | 35 | |
| Self-ConsistencyModel=GPT-OSS-20B2025.10 | 75 | 67 | 44 | 31 | 70 | 79 | 23 | |
| SID-vModel=LLaMA3.1-8B2025.10 | 67 | 43 | 40 | 18 | 41 | 64 | 31 | |
| SID-cModel=LLaMA3.1-8B2025.10 | 67 | 43 | 39 | 20 | 41 | 65 | 30 | |
| IOModel=LLaMA3.1-8B2025.10 | 65 | 37 | 35 | 15 | 46 | 59 | 28 | |
| SBPModel=GPT-OSS-20B2025.10 | 65 | 64 | 44 | 37 | 16 | 73 | 11 | |
| COTModel=LLaMA3.1-8B2025.10 | 61 | 38 | 34 | 14 | 37 | 54 | 28 | |
| MADModel=LLaMA3.1-8B2025.10 | 61 | 36 | 36 | 16 | 37 | 60 | 29 | |
| Self-ConsistencyModel=LLaMA3.1-8B2025.10 | 58 | 25 | 32 | 12 | 40 | 55 | 25 | |
| DMADModel=LLaMA3.1-8B2025.10 | 55 | 36 | 32 | 13 | 36 | 58 | 26 | |
| Self-ContrastModel=LLaMA3.1-8B2025.10 | 54 | 36 | 27 | 11 | 31 | 53 | 27 | |
| SBPModel=LLaMA3.1-8B2025.10 | 46 | 28 | 21 | 12 | 33 | 46 | 24 |