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

Interior Uniformity

Calculates task-area illuminance uniformity and adjacent-area illuminance ratios for interior workplace lighting checks.

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

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.

3
  • Task min illuminance

    task_min_illuminance_lux

    Minimum illuminance within the task area

    0 – 2000 lux
  • Task average illuminance

    task_average_illuminance_lux

    Average illuminance within the task area

    50 – 3000 lux
  • Surround average illuminance

    surround_average_illuminance_lux

    Average illuminance in the immediate surround area

    0 – 2000 lux

Hidden at higher difficulty

Visible in easier tasks and withheld in one or more harder tiers.

1
  • Background average illuminance

    background_average_illuminance_lux

    Average illuminance in the background area

    Hidden at hard difficulty.

    0 – 1000 lux

Scored outputs

3 outputs

Task uniformity uo

task_uniformity_uo

Task-area illuminance uniformity ratio

Scores if within ±3% of the reference value.

Surround to task ratio

surround_to_task_ratio

Immediate surround illuminance divided by task average illuminance

Scores if within ±3% of the reference value.

Background to task ratio

background_to_task_ratio

Background illuminance divided by task average illuminance

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.

easy

All inputs given

Office task area with all values visible

medium

All inputs given

Interior task area selected from office or industrial cases

hard

Some inputs hidden

Industrial task area with background illuminance embedded in context

Hidden inputs

  • Background average illuminance luxbackground_average_illuminance_lux

Prompt replacement text

Use the background-area illuminance implied by {{ archetype.description }}.

Background average illuminance lux restricted to: 180

Task bundle

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

/workspace

  • instruction.md
  • interior-uniformity_calc.py

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

1# ABOUTME: Prompt template for interior illuminance uniformity tasks.2# ABOUTME: Presents task, surround, and background illuminance values.3 4You are a senior interior lighting engineer verifying workplace illuminance uniformity.5 6## Given7 8| Parameter | Value | Unit |9|-----------|-------|------|10| Task minimum illuminance | {{ task_min_illuminance_lux }} | lux |11| Task average illuminance | {{ task_average_illuminance_lux }} | lux |12| Immediate surround average illuminance | {{ surround_average_illuminance_lux }} | lux |13| Background average illuminance | {{ background_average_illuminance_lux }} | lux |14 15## Constraints16 17- Task uniformity Uo equals task minimum illuminance divided by task average illuminance.18- Surround-to-task ratio equals immediate surround average illuminance divided by task average illuminance.19- Background-to-task ratio equals background average illuminance divided by task average illuminance.20 21## Output Format22 23Include a JSON block with exactly these keys:24 25```json26{27 "task_uniformity_uo": <numeric_value>,28 "surround_to_task_ratio": <numeric_value>,29 "background_to_task_ratio": <numeric_value>30}31```32 33Write your complete solution to `/workspace/output.md`.34

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 work area

office_work_area

Office task area with surrounding circulation

office-workplacetask-lighting
Parameter ranges
task_min_illuminance_lux
250 – 450
task_average_illuminance_lux
400 – 700
surround_average_illuminance_lux
250 – 500
background_average_illuminance_lux
100 – 250

Industrial work area

industrial_work_area

Industrial task area with adjacent general lighting

industrial-workplacetask-lighting
Parameter ranges
task_min_illuminance_lux
150 – 500
task_average_illuminance_lux
300 – 1000
surround_average_illuminance_lux
150 – 700
background_average_illuminance_lux
75 – 350

Example task

industrial-workplace-industrial-work-area-previewhard difficulty, some inputs hidden.

Industrial task area with adjacent general lighting. industrial-workplace. Required outputs: task_uniformity_uo, surround_to_task_ratio, background_to_task_ratio

The model sees

Scenario context and visible inputs.

task_min_illuminance_lux
150 to 500 lux
task_average_illuminance_lux
300 to 1000 lux
surround_average_illuminance_lux
150 to 700 lux

Executable tool: interior-uniformity_calc.py

The model must infer

Inputs withheld at this difficulty.

  • Background average illuminance lux

    background_average_illuminance_lux

Stand-in text in the prompt

Use the background-area illuminance implied by {{ archetype.description }}.

The model must produce

The scored JSON answer schema.

{
  "task_uniformity_uo": <number>,
  "surround_to_task_ratio": <number>,
  "background_to_task_ratio": <number>
}
  • task_uniformity_uo · scored within ±3%
  • surround_to_task_ratio · scored within ±3%
  • background_to_task_ratio · scored within ±3%