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

Egress Width

Calculates required egress width from occupant load and an explicit width-per-occupant criterion, then compares it with provided width. The template reports required width, margin, utilisation, and a numeric pass flag.

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

Standards

IBCNCC

Tags

deterministicegresslife-safetymechanicalwidth

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

3 inputs

Always given

Included directly in every task prompt.

3

  • Occupant load

    occupant_load

    Design occupant load

    1 – 100000 persons

  • Width per occupant mm

    width_per_occupant_mm

    Required egress width per occupant

    1 – 50 mm/person

  • Provided width

    provided_width_mm

    Provided aggregate egress width

    1 – 100000 mm

Scored outputs

4 outputs

Required width

required_width_mm

Required aggregate egress width

Scores if within ±3% of the reference value.

Provided margin

provided_margin_mm

Provided width minus required width

Scores if within ±3% of the reference value.

Utilisation ratio

utilisation_ratio

Required width divided by provided width

Scores if within ±3% of the reference value.

Width satisfies

width_satisfies

Numeric flag where 1 means the provided width satisfies the requirement

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 office exits
medium:
All parameters given across egress settings
hard:
All parameters given for high-occupancy concourses

Task bundle

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

/workspace

  • instruction.md
  • egress-width_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 fire and life-safety engineer specializing in egress design checks.2 3## Problem4 5Calculate required egress width from occupant load and an explicit width-per-occupant criterion.6 7## Given8 9| Parameter | Value | Unit |10|-----------|-------|------|11| Occupant load | {{ occupant_load }} | persons |12| Width per occupant | {{ width_per_occupant_mm }} | mm/person |13| Provided egress width | {{ provided_width_mm }} | mm |14 15{% if archetype_description is defined %}16### Egress Context17 18{{ archetype_description }}19{% endif %}20 21{% if tool_available %}22## Available Tool23 24An egress width calculation tool is available at `/workspace/{{ meta.name }}_calc.py`. Run it with:25 26```bash27python3 /workspace/{{ meta.name }}_calc.py --help28```29 30You may use this tool to verify your calculations or compute values directly.31{% endif %}32 33## Required34 35Calculate the following:36 371. Required egress width382. Provided width margin393. Width utilisation ratio404. Numeric pass flag, where 1 means the provided width satisfies the requirement41 42## Constraints43 44- No internet access is available. Work from engineering knowledge and the provided tool.45- Use required width = occupant load x width per occupant.46- Use only the explicit width-per-occupant criterion provided.47 48## Output Format49 50Show 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:51 52```json53{54 "required_width_mm": <numeric_value>,55 "provided_margin_mm": <numeric_value>,56 "utilisation_ratio": <numeric_value>,57 "width_satisfies": <numeric_value>58}59```60 61Write your complete solution to `/workspace/output.md`.62 63

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.

Office exit

office_exit

Office exit width check

office-exitcommercial-building
Parameter ranges
occupant_load
20 – 800
width_per_occupant_mm
4 – 8
provided_width_mm
800 – 8000

Station concourse

station_concourse

Station concourse egress width check

station-concoursepublic-transport
Parameter ranges
occupant_load
500 – 20000
width_per_occupant_mm
4 – 12
provided_width_mm
3000 – 60000

Example task

station-concourse-station-concourse-preview — hard difficulty, all inputs given.

Station concourse egress width check. station-concourse. Required outputs: required_width_mm, provided_margin_mm, utilisation_ratio, width_satisfies

The model sees

Scenario context and visible inputs.

occupant_load
500 to 20000 persons
width_per_occupant_mm
4 to 12 mm/person
provided_width_mm
3000 to 60000 mm

Executable tool: egress-width_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.

{
  "required_width_mm": <number>,
  "provided_margin_mm": <number>,
  "utilisation_ratio": <number>,
  "width_satisfies": <number>
}
  • required_width_mm · scored within ±3%
  • provided_margin_mm · scored within ±3%
  • utilisation_ratio · scored within ±3%
  • width_satisfies · scored within ±1%