Group-level distractor generation on MMLU Elementary Math
34.95Recall
Deepseek-V3
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2025.08 | 34.95 | |
2025.08 | 32.44 | |
2025.08 | 30.29 | |
2025.08 | 30.29 | |
2025.08 | 27.96 | |
2025.08 | 25.09 | |
2025.08 | 22.22 | |
2025.08 | 18.28 |
Deepseek-V3
| Method | Links | |
|---|---|---|
2025.08 | 34.95 | |
2025.08 | 32.44 | |
2025.08 | 30.29 | |
2025.08 | 30.29 | |
2025.08 | 27.96 | |
2025.08 | 25.09 | |
2025.08 | 22.22 | |
2025.08 | 18.28 |