Comparing Mistral-Medium in different instance.
WARNING: the model Albert is not a mistral-medium but a mistral-small model, check the experiment detail to see the full model parameters list.
This dataset contains 12 experiments
from the EvalAP evaluation platform.
Datasets: Assistant IA - QA, MFS_questions_v01
Models evaluated: mistral-medium-2508, mistralai/Mistral-Small-3.2-24B-Instruct-2506
Metrics: energy_consumption… See the full description on the dataset page:
https://huggingface.co/datasets/AgentPublic/evalap-comparing-mistral-medium-106.
