Arithmetic Reasoning on GSM Reversed
90.3Accuracy
GPT-4o
Updated 4d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2025.12 | 90.3 | |
2025.12 | 87.8 | |
2025.12 | 87.6 | |
2025.12 | 87.5 | |
2025.12 | 76.2 | |
2025.12 | 34.1 | |
2025.12 | 29.1 |
GPT-4o
| Method | Links | |
|---|---|---|
2025.12 | 90.3 | |
2025.12 | 87.8 | |
2025.12 | 87.6 | |
2025.12 | 87.5 | |
2025.12 | 76.2 | |
2025.12 | 34.1 | |
2025.12 | 29.1 |