Chatbot Evaluation on Vicuna benchmark
13,481Elo Rating
GPT-4
Updated 4d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2023.05 | 13,481 | |
2023.05 | 10,221 | |
2023.05 | 9,921 | |
2023.05 | 9,741 | |
2023.05 | 9,661 | |
2023.05 | 9,161 | |
2023.05 | 9,021 | |
2023.05 | 8,791 |
GPT-4
| Method | Links | |
|---|---|---|
2023.05 | 13,481 | |
2023.05 | 10,221 | |
2023.05 | 9,921 | |
2023.05 | 9,741 | |
2023.05 | 9,661 | |
2023.05 | 9,161 | |
2023.05 | 9,021 | |
2023.05 | 8,791 |