LLM Evaluation on Suite of Benchmarks (MMLU, IFEval, GSM8K, MATH, HumanEval, MBPP, Hellaswag, GPQA)
51.94MMLU
Alpaca-GPT4
Updated 23d ago
Evaluation Results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
2025.08 | 51.94 | 38.68 | 50.87 | 10.28 | 17.07 | 43.6 | 63.02 | 0.51 | 34.5 | |
2025.08 | 51.32 | 43.2 | 51.18 | 12.92 | 39.63 | 41.8 | 58.78 | 16.67 | 39.63 | |
2025.08 | 47.46 | 41.09 | 35.63 | 4.96 | 39.63 | 37.4 | 48.11 | 5.56 | 32.48 | |
2025.08 | 47.21 | 43.92 | 43.9 | 4.2 | 29.27 | 43.4 | 60.17 | 5.56 | 34.7 | |
2025.08 | 46.12 | 46.14 | 53.3 | 12.72 | 40.24 | 48 | 53.05 | 12.12 | 38.96 | |
2025.08 | 44.69 | 47.96 | 57.62 | 18.5 | 52.44 | 45.4 | 57.37 | 19.7 | 42.96 | |
2025.08 | 43.47 | 40.78 | 65.2 | 15.58 | 51.83 | 47.6 | 58.65 | 17.68 | 42.6 | |
2025.08 | 41.5 | 45.66 | 60.8 | 20.06 | 46.34 | 48 | 55.01 | 24.75 | 42.77 | |
2025.08 | 39.96 | 37.8 | 44.5 | 5.38 | 40.85 | 44 | 42.38 | 27.27 | 35.27 | |
2025.08 | 37.71 | 34.35 | 53.68 | 11 | 9.15 | 45.6 | 57.81 | 2.53 | 31.48 | |
2025.08 | 33.98 | 48.82 | 43.82 | 6.06 | 35.98 | 42.4 | 44.5 | 18.18 | 34.22 | |
2025.08 | 25.51 | 14.75 | 56.33 | 16.56 | 13.41 | 45.6 | 25.83 | 0 | 24.75 | |
2025.08 | 23.61 | 29.61 | 43.14 | 8.28 | 32.32 | 32.6 | 41.83 | 0 | 26.42 |