General Intelligence Evaluation (3-shot) on AGIEval (test)
27AGIEval (3-shot)
Full FT
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2025.03 | 27 | |
2025.03 | 26.5 | |
2025.03 | 26.1 | |
2025.03 | 25.7 | |
2025.03 | 25.6 | |
2025.03 | 24.7 | |
2025.03 | 24.4 | |
2025.03 | 21.8 |
Full FT
| Method | Links | |
|---|---|---|
2025.03 | 27 | |
2025.03 | 26.5 | |
2025.03 | 26.1 | |
2025.03 | 25.7 | |
2025.03 | 25.6 | |
2025.03 | 24.7 | |
2025.03 | 24.4 | |
2025.03 | 21.8 |