Factual Knowledge on MMLU-Pro (test)
24.5Accuracy
Alpaca-GPT4 + NAIT (GSM)
Updated 1mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.03 | 24.5 | 37.7 | 4.65 | |
2026.03 | 23.61 | 37.18 | 3.2 | |
2026.03 | 23.46 | 37.06 | 2.88 | |
2026.03 | 23.36 | 36.47 | 1.23 | |
2026.03 | 23.29 | 37.2 | 3.24 | |
2026.03 | 23.04 | 36.17 | 0.39 | |
2026.03 | 22.86 | 37.16 | 3.15 | |
2026.03 | 22.82 | 36.71 | 1.89 | |
2026.03 | 21.96 | 35.18 | -2.34 | |
2026.03 | 21.89 | 36.03 | - | |
2026.03 | 21.5 | 35.68 | -0.98 | |
| 21.43 | 35.69 | -0.94 |