LIVEdataset aec-bench@releasetasks 552models 18last submission … · built …
mechanicalwith-tool

Mass Balance

Calculates global mass balance closure from two inlet and two outlet streams using an explicit closure tolerance. The template reports total inlet, total outlet, imbalance, closure error percentage, and a numeric closure flag.

with-tool: The model is given an executable Python calculator script.

Standards

ISO 15926

Tags

closuredeterministicmass-balancemechanicalprocess

How this task is generated

One template produces many comparable benchmark tasks while keeping the scoring contract fixed.

  1. 01

    Template

    The reusable contract shown on this page.

  2. 02

    Scenario

    An archetype and site context are sampled.

  3. 03

    Difficulty tier

    Inputs may be hidden at harder tiers.

  4. 04

    Task prompt

    The model responds with the declared outputs.

Parameters

Inputs the model receives, and the outputs it is scored on.

Inputs

5 inputs

Always given

Included directly in every task prompt.

5

  • Inlet 1

    inlet_1_kg_h

    First inlet mass flow

    0 – 100000000 kg/h

  • Inlet 2

    inlet_2_kg_h

    Second inlet mass flow

    0 – 100000000 kg/h

  • Outlet 1

    outlet_1_kg_h

    First outlet mass flow

    0 – 100000000 kg/h

  • Outlet 2

    outlet_2_kg_h

    Second outlet mass flow

    0 – 100000000 kg/h

  • Closure tolerance pct

    closure_tolerance_pct

    Allowed absolute closure error percentage

    0 – 20 %

Scored outputs

5 outputs

Total inlet kg h

total_inlet_kg_h

Total inlet mass flow

Scores if within ±3% of the reference value.

Total outlet kg h

total_outlet_kg_h

Total outlet mass flow

Scores if within ±3% of the reference value.

Imbalance kg h

imbalance_kg_h

Mass imbalance, positive when inlet exceeds outlet

Scores if within ±3% of the reference value.

Closure error pct

closure_error_pct

Absolute closure error percentage

Scores if within ±3% of the reference value.

Closure satisfied

closure_satisfied

Numeric flag where 1 means closure is within tolerance

Scores if within ±1% of the reference value.

Difficulty

Each template is sampled at three tiers. Harder tiers may hide inputs, forcing the model to infer them from the scenario description.

All inputs remain visible at every tier

For this template, difficulty scales through parameter and scenario ranges rather than hidden information.

easy:
All parameters given for a process unit
medium:
All parameters given across process balance settings
hard:
All parameters given for treatment train balances

Task bundle

The exact instruction and parameter contract used to generate this task, pinned to the published library source.

/workspace

  • instruction.md
  • mass-balance_calc.py

Teal lines show Jinja input conditions, not task visibility policy. A line renders only when that input or tool is visible.

1You are a senior mechanical process engineer specializing in process balance checks.2 3## Problem4 5Check global mass balance closure from two inlet streams, two outlet streams, and an explicit closure tolerance.6 7## Given8 9| Parameter | Value | Unit |10|-----------|-------|------|11| Inlet stream 1 | {{ inlet_1_kg_h }} | kg/h |12| Inlet stream 2 | {{ inlet_2_kg_h }} | kg/h |13| Outlet stream 1 | {{ outlet_1_kg_h }} | kg/h |14| Outlet stream 2 | {{ outlet_2_kg_h }} | kg/h |15| Closure tolerance | {{ closure_tolerance_pct }} | % |16 17{% if archetype_description is defined %}18### Process Context19 20{{ archetype_description }}21{% endif %}22 23{% if tool_available %}24## Available Tool25 26A mass balance calculation tool is available at `/workspace/{{ meta.name }}_calc.py`. Run it with:27 28```bash29python3 /workspace/{{ meta.name }}_calc.py --help30```31 32You may use this tool to verify your calculations or compute values directly.33{% endif %}34 35## Required36 37Calculate total inlet flow, total outlet flow, imbalance, closure error percentage, and numeric pass flag.38 39## Constraints40 41- No internet access is available. Work from engineering knowledge and the provided tool.42- Use imbalance = total inlet - total outlet.43- Use closure error = absolute imbalance / total inlet x 100.44- Use only the explicit closure tolerance provided.45 46## Output Format47 48Show your step-by-step working in Markdown. At the end of your solution, include a JSON block with your final answers in exactly this format:49 50```json51{52 "total_inlet_kg_h": <numeric_value>,53 "total_outlet_kg_h": <numeric_value>,54 "imbalance_kg_h": <numeric_value>,55 "closure_error_pct": <numeric_value>,56 "closure_satisfied": <numeric_value>57}58```59 60Write your complete solution to `/workspace/output.md`.61 62

Scenario archetypes

Each generated task is drawn from one of these realistic scenario bands.

Site contexts ground each scenario in a real locale the model can use to infer hidden values.

Process unit

process_unit

Industrial process unit mass balance

process-unitsteady-state-model
Parameter ranges
inlet_1_kg_h
100 – 100000
inlet_2_kg_h
0 – 50000
outlet_1_kg_h
100 – 100000
outlet_2_kg_h
0 – 50000
closure_tolerance_pct
0.1 – 5

Treatment train

treatment_train

Water or wastewater treatment train mass balance

treatment-trainprocess-simulation
Parameter ranges
inlet_1_kg_h
1000 – 1000000
inlet_2_kg_h
0 – 250000
outlet_1_kg_h
1000 – 1000000
outlet_2_kg_h
0 – 250000
closure_tolerance_pct
0.1 – 3

Example task

treatment-train-treatment-train-preview — hard difficulty, all inputs given.

Water or wastewater treatment train mass balance. treatment-train. Required outputs: total_inlet_kg_h, total_outlet_kg_h, imbalance_kg_h, closure_error_pct, closure_satisfied

The model sees

Scenario context and visible inputs.

inlet_1_kg_h
1000 to 1e+06 kg/h
inlet_2_kg_h
0 to 250000 kg/h
outlet_1_kg_h
1000 to 1e+06 kg/h
outlet_2_kg_h
0 to 250000 kg/h
closure_tolerance_pct
0.1 to 3 %

Executable tool: mass-balance_calc.py

The model must infer

Inputs withheld at this difficulty.

Nothing. All inputs are supplied.

The model must produce

The scored JSON answer schema.

{
  "total_inlet_kg_h": <number>,
  "total_outlet_kg_h": <number>,
  "imbalance_kg_h": <number>,
  "closure_error_pct": <number>,
  "closure_satisfied": <number>
}
  • total_inlet_kg_h · scored within ±3%
  • total_outlet_kg_h · scored within ±3%
  • imbalance_kg_h · scored within ±3%
  • closure_error_pct · scored within ±3%
  • closure_satisfied · scored within ±1%