Coding on Code Benchmarks Aggregate
37.5ScoreLLAMA 2
Evaluation Results
| Method | Links | |
|---|---|---|
| LLAMA 2Size=70B2023.07 | 37.5 | |
| LLAMA 1Size=65B2023.07 | 30.7 | |
| MPTSize=30B2023.07 | 28.9 | |
| LLAMA 2Size=34B2023.07 | 27.8 | |
| LLAMA 1Size=33B2023.07 | 26 | |
| LLAMA 2Size=13B2023.07 | 24.5 | |
| MPTSize=7B2023.07 | 20.5 | |
| LLAMA 1Size=13B2023.07 | 18.9 | |
| LLAMA 2Size=7B2023.07 | 16.8 | |
| FalconSize=40B2023.07 | 15.2 | |
| LLAMA 1Size=7B2023.07 | 14.1 | |
| FalconSize=7B2023.07 | 5.6 |