from dataclasses import dataclass from enum import Enum @dataclass class Task: benchmark: str metric: str col_name: str # Select your tasks here # --------------------------------------------------- class Tasks(Enum): # task_key in the json file, metric_key in the json file, name to display in the leaderboard task0 = Task("acc_overall", "acc", "Acc_All") task1 = Task("acc_sel", "acc_sel", "Acc_Sel") task2 = Task("acc_el", "acc_el", "Acc_El") task3 = Task("acc_perturb", "perturb_score", "Acc_Perturb") task4 = Task("score_consistency", "consist_score", "Consistency_Score") class AssetTasks(Enum): # task_key in the json file, metric_key in the json file, name to display in the leaderboard task0 = Task("acc_electric_motor", "acc_electric_motor", "acc_electric_motor") task1 = Task("acc_steam_turbine", "acc_steam_turbine", "acc_steam_turbine") task2 = Task("acc_aero_gas_turbine", "acc_aero_gas_turbine", "acc_aero_gas_turbine") task3 = Task("acc_industrial_gas_turbine", "acc_industrial_gas_turbine", "acc_industrial_gas_turbine") task4 = Task("acc_pump", "acc_pump", "acc_pump") task5 = Task("acc_compressor", "acc_compressor", "acc_compressor") task6 = Task("acc_reciprocating_internal_combustion_engine", "acc_reciprocating_internal_combustion_engine", "acc_reciprocating_internal_combustion_engine") task7 = Task("acc_electric_generator", "acc_electric_generator", "acc_electric_generator") task8 = Task("acc_fan", "acc_fan", "acc_fan") task9 = Task("acc_power_transformer", "acc_power_transformer", "acc_power_transformer") class UncertaintyTasks(Enum): # task_key in the json file, metric_key in the json file, name to display in the leaderboard task0 = Task("fmsr_ss", "fmsr_ss", "fmsr_ss") task1 = Task("fmsr_coverage_rate", "fmsr_coverage_rate", "fmsr_coverage_rate") task2 = Task("fmsr_acc", "fmsr_acc", "fmsr_acc") task3 = Task("fmsr_uacc", "fmsr_uacc", "fmsr_uacc") # { # "acc_overall": { # "acc": 0.38732658417697785 # }, # "acc_sel": { # "acc_sel": 0.40638297872340423 # }, # "acc_el": { # "acc_el": 0.4954128440366973 # }, # "acc_perturb": { # "perturb_score": 0.2819647544056993 # }, # "score_consistency": { # "consist_score": 0.16422947131608548 # }, # "uncertainty": { # "uncertainty_score": 0 # }, # "acc_electric_motor": { # "acc_electric_motor": 0.41025641025641024 # }, # "acc_steam_turbine": { # "acc_steam_turbine": 0.30409356725146197 # }, # "acc_aero_gas_turbine": { # "acc_aero_gas_turbine": 0.3541666666666667 # }, # "acc_industrial_gas_turbine": { # "acc_industrial_gas_turbine": 0.45 # }, # "acc_pump": { # "acc_pump": 0.39473684210526316 # }, # "acc_compressor": { # "acc_compressor": 0.35 # }, # "acc_reciprocating_internal_combustion_engine": { # "acc_reciprocating_internal_combustion_engine": 0.47619047619047616 # }, # "acc_electric_generator": { # "acc_electric_generator": 0.42735042735042733 # }, # "acc_fan": { # "acc_fan": 0.445 # }, # "acc_power_transformer": { # "acc_power_transformer": 0.3161764705882353 # } # } NUM_FEWSHOT = 0 # Change with your few shot # --------------------------------------------------- # Your leaderboard name TITLE = """

FailureSensorIQ leaderboard

""" # What does your leaderboard evaluate? INTRODUCTION_TEXT = """ **FailureSensorIQ** is a quiz designed for AI models to test how well they understand when and why industrial machines might fail. Instead of asking general trivia, it asks real-world questions like: > “If this machine experiences this failure mode, which sensor would detect it first?” Or the reverse: > “If this sensor shows a strange reading, what might be going wrong?” """ # Which evaluations are you running? how can people reproduce what you have? LLM_BENCHMARKS_TEXT = ''' ## Prompt Format The prompt will follow the following style. Models' output are expected to follow this format. ``` Select the correct option(s) from the following options given the question. To solve the problem, follow the Let's think Step by Step reasoning strategy. Question: For electric motor, if a failure event rotor windings fault occurs, which sensor out of the choices is the most relevant sensor regarding the occurrence of the failure event? Options: A partial discharge B resistance C oil debris D current E voltage {"step_1": "", "step_2": "", "step_n": "", "answer": } Your output in a single line: ``` ## Expected Output Format ``` {"step_1": "", "step_2": "", "step_n": "", "answer": } ``` ## Reproducibility To reproduce our results, here is the commands you can run: ''' print(LLM_BENCHMARKS_TEXT) EVALUATION_QUEUE_TEXT = """ ## Some good practices before submitting a model ### 1) Make sure you can load your model and tokenizer using AutoClasses: ```python from transformers import AutoConfig, AutoModel, AutoTokenizer config = AutoConfig.from_pretrained("your model name", revision=revision) model = AutoModel.from_pretrained("your model name", revision=revision) tokenizer = AutoTokenizer.from_pretrained("your model name", revision=revision) ``` If this step fails, follow the error messages to debug your model before submitting it. It's likely your model has been improperly uploaded. Note: make sure your model is public! Note: if your model needs `use_remote_code=True`, we do not support this option yet but we are working on adding it, stay posted! ### 2) Convert your model weights to [safetensors](https://huggingface.co/docs/safetensors/index) It's a new format for storing weights which is safer and faster to load and use. It will also allow us to add the number of parameters of your model to the `Extended Viewer`! ### 3) Make sure your model has an open license! This is a leaderboard for Open LLMs, and we'd love for as many people as possible to know they can use your model 🤗 ### 4) Fill up your model card When we add extra information about models to the leaderboard, it will be automatically taken from the model card ## In case of model failure If your model is displayed in the `FAILED` category, its execution stopped. Make sure you have followed the above steps first. If everything is done, check you can launch the EleutherAIHarness on your model locally, using the above command without modifications (you can add `--limit` to limit the number of examples per task). """ CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results" CITATION_BUTTON_TEXT = r""" @article{constantinides2025failuresensoriq, title={FailureSensorIQ: A Multi-Choice QA Dataset for Understanding Sensor Relationships and Failure Modes}, author={Constantinides, Christodoulos and Patel, Dhaval and Lin, Shuxin and Guerrero, Claudio and Patil, Sunil Dagajirao and Kalagnanam, Jayant}, journal={arXiv preprint arXiv:2506.03278}, year={2025} } """