LLM Performance Estimation on GSM8K (test)
1.619MAE (%)
SparseEval
Updated 4d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.02 | 1.619 | 0.936 | |
2026.02 | 1.754 | 0.931 | |
2026.02 | 1.96 | 0.925 | |
2026.02 | 2.321 | 0.908 | |
2026.02 | 2.424 | 0.887 | |
2026.02 | 2.774 | 0.88 | |
2026.02 | 2.778 | 0.906 | |
2026.02 | 3.161 | 0.871 | |
2026.02 | 3.305 | 0.872 | |
2026.02 | 3.631 | 0.916 | |
2026.02 | 3.756 | 0.878 | |
2026.02 | 3.984 | 0.832 | |
2026.02 | 4.003 | 0.9 | |
2026.02 | 4.157 | 0.885 | |
2026.02 | 4.203 | 0.912 | |
2026.02 | 4.271 | 0.892 | |
2026.02 | 4.433 | 0.844 | |
2026.02 | 5.275 | 0.802 | |
2026.02 | 5.295 | 0.842 | |
2026.02 | 5.412 | 0.833 |