GSM-Infinite
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Mathematical Reasoning | GSM-Infinite (Avg) | Accuracy17.1 | 24 | |
| Mathematical Reasoning | GSM-Infinite 32K | Accuracy15.4 | 24 | |
| Mathematical Reasoning | GSM-Infinite 16K | Accuracy16.2 | 24 | |
| Mathematical Reasoning | GSM-Infinite (8K) | Accuracy22.9 | 24 | |
| Mathematical Reasoning | GSM-Infinite | Accuracy (8K)22.9 | 17 | |
| Mathematical Reasoning | GSM-Infinite Hard | Accuracy50.4 | 16 | |
| Long-Context Mathematical Reasoning | GSM-Infinite | Accuracy87.06 | 11 |
Showing 7 of 7 rows