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
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 69.49 |
| AI2 Reasoning Challenge (25-Shot) | 66.47 |
| HellaSwag (10-Shot) | 85.91 |
| MMLU (5-Shot) | 64.48 |
| TruthfulQA (0-shot) | 59.98 |
| Winogrande (5-shot) | 78.53 |
| GSM8k (5-shot) | 61.56 |
- Downloads last month
- 62
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard66.470
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard85.910
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard64.480
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard59.980
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard78.530
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard61.560