Motion Policy Classification on ParlVote+
0.47Macro F1Mistral-7B-Instruct-v0.3
Evaluation Results
| Method | Links | |
|---|---|---|
| Mistral-7B-Instruct-v0.3Evaluation Protocol=fine-tuning2025.08 | 0.47 | |
| Llama-3.1-8B-InstructEvaluation Protocol=fine-tuning2025.08 | 0.35 | |
| gemma-3-4b-itEvaluation Protocol=fine-tuning2025.08 | 0.26 | |
| Llama-3.1-8B-InstructEvaluation Protocol=3-shot2025.08 | 0.08 | |
| gemma-3-4b-itEvaluation Protocol=3-shot2025.08 | 0.07 | |
| Mistral-7B-Instruct-v0.3Evaluation Protocol=3-shot2025.08 | 0.05 | |
| gpt-4.1-nanoEvaluation Protocol=3-shot2025.08 | 0.03 | |
| gemma-3-4b-itEvaluation Protocol=one-shot2025.08 | 0.02 | |
| Llama-3.1-8B-InstructEvaluation Protocol=one-shot2025.08 | 0.02 | |
| Mistral-7B-Instruct-v0.3Evaluation Protocol=one-shot2025.08 | 0.01 | |
| gpt-4.1-nanoEvaluation Protocol=one-shot2025.08 | 0 |