Knowledge Assessment on LAMA-based Knowledge Assessment (test)
23.06KaRR ScoreOPT
Evaluation results
| Method | Links | |
|---|---|---|
| OPTSize=175B2023.05 | 23.06 | |
| LLaMA2Size=65B2023.05 | 19.71 | |
| VicunaSize=13B2023.05 | 19.5 | |
| WizardLMSize=13B2023.05 | 16.9 | |
| DollySize=12B2023.05 | 15.6 | |
| LLaMASize=65B2023.05 | 14.56 | |
| LLaMASize=13B2023.05 | 13.86 | |
| GPT-NEOSize=2.65B2023.05 | 13.44 | |
| LLaMASize=7B2023.05 | 12.37 | |
| GPT2-XLSize=1.56B2023.05 | 12.27 | |
| MossSize=16B2023.05 | 11.2 | |
| Phi-1.5Size=1.3B2023.05 | 10.58 | |
| GPTSize=0.12B2023.05 | 9.57 | |
| T5-3BSize=3B2023.05 | 9.52 | |
| AlpacaSize=13B2023.05 | 8.24 | |
| FalconSize=7B2023.05 | 7.97 | |
| BLOOMSize=7B2023.05 | 7.72 | |
| XLNetSize=0.12B2023.05 | 5.86 | |
| GLMSize=10B2023.05 | 5.59 | |
| T5-largeSize=0.74B2023.05 | 3.22 |