Reasoning Episode Classification on Omni-MATH Non-Reasoning episodes (human-annotated gold set)
89.34Accuracy
GPT-4.1
Updated 4d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2025.12 | 89.34 | 85.36 | |
2025.12 | 89.34 | 85.35 | |
2025.12 | 87.16 | 82.35 | |
2025.12 | 84.43 | 78.62 |
GPT-4.1
| Method | Links | ||
|---|---|---|---|
2025.12 | 89.34 | 85.36 | |
2025.12 | 89.34 | 85.35 | |
2025.12 | 87.16 | 82.35 | |
2025.12 | 84.43 | 78.62 |