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

Water Supply Curve

Develops a hydrant water supply curve from static pressure, residual pressure, and measured test flow using the standard 0.54 flow-test exponent. The template reports the curve coefficient, target residual flow, and available flow at 20 psi.

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

Standards

NFPA 13NFPA 291

Tags

deterministicfire-serviceshydrantmechanicalwater-supply

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

4 inputs

Always given

Included directly in every task prompt.

4

  • Static pressure

    static_pressure_psi

    Static pressure before flow test

    1 – 300 psi

  • Residual pressure

    residual_pressure_psi

    Residual pressure during flow test

    0 – 250 psi

  • Test flow

    test_flow_gpm

    Measured test flow

    1 – 20000 gpm

  • Target residual pressure

    target_residual_pressure_psi

    Target residual pressure

    0 – 250 psi

Scored outputs

4 outputs

Pressure drop test psi

pressure_drop_test_psi

Pressure drop during the flow test

Scores if within ±3% of the reference value.

Curve coefficient

curve_coefficient

Water supply curve coefficient

Scores if within ±3% of the reference value.

Flow at target residual gpm

flow_at_target_residual_gpm

Flow at the target residual pressure

Scores if within ±3% of the reference value.

Available flow 20psi gpm

available_flow_20psi_gpm

Available flow at 20 psi residual pressure

Scores if within ±3% 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 municipal hydrant
medium:
All parameters given across hydrant supply curves
hard:
All parameters given for an industrial fire main

Task bundle

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

/workspace

  • instruction.md
  • water-supply-curve_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 engineer specializing in fire protection hydraulics.2 3## Task4 5Develop the water supply curve for the hydrant flow test in {{ site_context }}.6 7## Given8 9| Parameter | Value | Unit |10| --- | ---: | --- |11| Static pressure | {{ static_pressure_psi }} | psi |12| Residual pressure during test | {{ residual_pressure_psi }} | psi |13| Measured test flow | {{ test_flow_gpm }} | gpm |14| Target residual pressure | {{ target_residual_pressure_psi }} | psi |15 16## Constraints17 18- No internet access is available.19- Use `Q = K * (P_static - P_residual)^0.54`.20- Calculate `K` from the measured test point.21- Calculate available flow at 20 psi residual pressure using the same curve.22 23{% if tool_available %}24## Available Tool25 26A 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:38 39- Pressure drop during the flow test (`pressure_drop_test_psi`)40- Water supply curve coefficient (`curve_coefficient`)41- Flow at the target residual pressure (`flow_at_target_residual_gpm`)42- Available flow at 20 psi residual pressure (`available_flow_20psi_gpm`)43 44## Output Format45 46Show 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:47 48```json49{50 "pressure_drop_test_psi": <numeric_value>,51 "curve_coefficient": <numeric_value>,52 "flow_at_target_residual_gpm": <numeric_value>,53 "available_flow_20psi_gpm": <numeric_value>54}55```56 57Write your complete solution to `/workspace/output.md`.58

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.

Municipal hydrant

municipal_hydrant

Municipal hydrant water supply curve

municipal-hydrantstreet-main-flow-test
Parameter ranges
static_pressure_psi
80 – 140
residual_pressure_psi
20 – 70
test_flow_gpm
500 – 3000
target_residual_pressure_psi
20 – 60

Industrial fire main

industrial_fire_main

Industrial fire-main water supply curve

industrial-fire-mainsite-hydrant-flow-test
Parameter ranges
static_pressure_psi
120 – 220
residual_pressure_psi
30 – 100
test_flow_gpm
1000 – 8000
target_residual_pressure_psi
20 – 80

Example task

industrial-fire-main-industrial-fire-main-preview — hard difficulty, all inputs given.

Industrial fire-main water supply curve. industrial-fire-main. Required outputs: pressure_drop_test_psi, curve_coefficient, flow_at_target_residual_gpm, available_flow_20psi_gpm

The model sees

Scenario context and visible inputs.

static_pressure_psi
120 to 220 psi
residual_pressure_psi
30 to 100 psi
test_flow_gpm
1000 to 8000 gpm
target_residual_pressure_psi
20 to 80 psi

Executable tool: water-supply-curve_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.

{
  "pressure_drop_test_psi": <number>,
  "curve_coefficient": <number>,
  "flow_at_target_residual_gpm": <number>,
  "available_flow_20psi_gpm": <number>
}
  • pressure_drop_test_psi · scored within ±3%
  • curve_coefficient · scored within ±3%
  • flow_at_target_residual_gpm · scored within ±3%
  • available_flow_20psi_gpm · scored within ±3%