Commonsense Reasoning on Commonsense Reasoning Benchmarks Aggregate
71.9ScoreLLAMA 2
Evaluation Results
| Method | Links | |
|---|---|---|
| LLAMA 2Size=70B2023.07 | 71.9 | |
| LLAMA 1Size=65B2023.07 | 70.7 | |
| LLAMA 1Size=33B2023.07 | 70 | |
| LLAMA 2Size=34B2023.07 | 69.9 | |
| FalconSize=40B2023.07 | 69.2 | |
| LLAMA 2Size=13B2023.07 | 66.9 | |
| LLAMA 1Size=13B2023.07 | 66.1 | |
| MPTSize=30B2023.07 | 64.9 | |
| LLAMA 2Size=7B2023.07 | 63.9 | |
| LLAMA 1Size=7B2023.07 | 60.8 | |
| MPTSize=7B2023.07 | 57.4 | |
| FalconSize=7B2023.07 | 56.1 |