---
license: mit
language:
- en
- de
---
This Model was just an Test Train to see how our new Training Algorithm and Data does like.

Model is based on Mistral v0.1

As this was an test run, we just tested it and heres the Data, the model hasnt Improved any better.

| Model | Turn 1 Score | Turn 2 Score | Average Score |
|-------|-------------|-------------|---------------|
| gpt-4 | 8.95625      | 9.025000     | 8.990625       |
| gpt-3.5-turbo | 8.075000     | 7.943750     | 7.943750       |
| claude-v1  | 8.150000     | 7.900000     | 8.025000       |
| **LexGPT-V3** | **8.14375**      | 7.719355     | 7.926667       |
| vicuna-13b-v1.3 | 6.812500    | 5.962500     | 6.387500       |

Open-LLM Leaderboard Results:
[Results](https://huggingface.co/datasets/open-llm-leaderboard/details_lex-hue__LexGPT-V3)