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

Lux Level Calculation

Calculates reduced room lighting performance using the lumen method. The template uses room area, luminaire count, luminous flux, utilisation factor, maintenance factor, total lighting power, and target illuminance to report average illuminance, uniformity, power density, and target margin.

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

9 inputs

Always given

Included directly in every task prompt.

8
Show 8 inputs
  • Room length

    room_length_m

    Room length

    2 – 100 m
  • Room width

    room_width_m

    Room width

    2 – 80 m
  • Luminaire

    luminaire_count

    Number of luminaires

    1 – 500 count
  • Luminaire luminous flux

    luminaire_luminous_flux_lm

    Luminous flux per luminaire

    500 – 80000 lm
  • Maintenance factor

    maintenance_factor

    Maintenance factor

    0.5 – 0.95
  • Total lighting power

    total_lighting_power_w

    Total installed lighting power

    20 – 100000 W
  • Minimum illuminance

    minimum_illuminance_lux

    Minimum calculated illuminance

    0 – 2000 lux
  • Target illuminance

    target_illuminance_lux

    Target average illuminance

    50 – 2000 lux

Hidden at higher difficulty

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

1
  • Utilisation factor

    utilisation_factor

    Utilisation factor

    Hidden at hard difficulty.

    0.2 – 0.9

Scored outputs

4 outputs

Average illuminance lux

average_illuminance_lux

Average maintained illuminance

Scores if within ±3% of the reference value.

Uniformity ratio uo

uniformity_ratio_uo

Minimum to average illuminance uniformity ratio

Scores if within ±3% of the reference value.

Specific luminaire power density w m2 100lux

specific_luminaire_power_density_w_m2_100lux

Lighting power density normalised to 100 lux

Scores if within ±3% of the reference value.

Target illuminance margin pct

target_illuminance_margin_pct

Percentage margin against target 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 room with all values visible

medium

All inputs given

Room lighting case selected from office or warehouse layouts

hard

Some inputs hidden

Warehouse lighting case with utilisation factor embedded in context

Hidden inputs

  • Utilisation factorutilisation_factor

Prompt replacement text

Use the utilisation factor implied by {{ archetype.description }}.

Utilisation factor restricted to: 0.62

Task bundle

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

/workspace

  • instruction.md
  • lux-level-calculation_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 room lumen-method illuminance tasks.2# ABOUTME: Presents room, luminaire, utilisation, maintenance, and target inputs.3 4You are a senior building lighting engineer checking a reduced lumen-method calculation.5 6## Given7 8| Parameter | Value | Unit |9|-----------|-------|------|10| Room length | {{ room_length_m }} | m |11| Room width | {{ room_width_m }} | m |12| Luminaire count | {{ luminaire_count }} | count |13| Luminaire luminous flux | {{ luminaire_luminous_flux_lm }} | lm |14| Utilisation factor | {{ utilisation_factor }} | - |15| Maintenance factor | {{ maintenance_factor }} | - |16| Total lighting power | {{ total_lighting_power_w }} | W |17| Minimum illuminance | {{ minimum_illuminance_lux }} | lux |18| Target illuminance | {{ target_illuminance_lux }} | lux |19 20## Constraints21 22- Room area equals length times width.23- Average illuminance equals total lamp lumens times utilisation factor times maintenance factor divided by room area.24- Uniformity ratio equals minimum illuminance divided by average illuminance.25- Specific luminaire power density equals total power divided by room area and divided by average illuminance per 100 lux.26- Target margin is the percentage difference between average and target illuminance.27 28## Output Format29 30Include a JSON block with exactly these keys:31 32```json33{34 "average_illuminance_lux": <numeric_value>,35 "uniformity_ratio_uo": <numeric_value>,36 "specific_luminaire_power_density_w_m2_100lux": <numeric_value>,37 "target_illuminance_margin_pct": <numeric_value>38}39```40 41Write your complete solution to `/workspace/output.md`.42

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 room

office_room

Office room lighting layout

office-lightinglumen-method
Parameter ranges
room_length_m
6 – 30
room_width_m
4 – 20
luminaire_count
4 – 80
luminaire_luminous_flux_lm
2500 – 10000
utilisation_factor
0.45 – 0.75
maintenance_factor
0.7 – 0.9
total_lighting_power_w
100 – 5000
minimum_illuminance_lux
150 – 500
target_illuminance_lux
200 – 500

Warehouse room

warehouse_room

Warehouse lighting layout

warehouse-lightinglumen-method
Parameter ranges
room_length_m
20 – 100
room_width_m
10 – 60
luminaire_count
20 – 300
luminaire_luminous_flux_lm
8000 – 60000
utilisation_factor
0.4 – 0.75
maintenance_factor
0.6 – 0.85
total_lighting_power_w
1000 – 50000
minimum_illuminance_lux
75 – 300
target_illuminance_lux
100 – 400

Example task

warehouse-lighting-warehouse-room-previewhard difficulty, some inputs hidden.

Warehouse lighting layout. warehouse-lighting. Required outputs: average_illuminance_lux, uniformity_ratio_uo, specific_luminaire_power_density_w_m2_100lux, target_illuminance_margin_pct

The model sees

Scenario context and visible inputs.

room_length_m
20 to 100 m
room_width_m
10 to 60 m
luminaire_count
20 to 300 count
luminaire_luminous_flux_lm
8000 to 60000 lm
maintenance_factor
0.6 to 0.85 -
total_lighting_power_w
1000 to 50000 W
minimum_illuminance_lux
75 to 300 lux
target_illuminance_lux
100 to 400 lux

Executable tool: lux-level-calculation_calc.py

The model must infer

Inputs withheld at this difficulty.

  • Utilisation factor

    utilisation_factor

Stand-in text in the prompt

Use the utilisation factor implied by {{ archetype.description }}.

The model must produce

The scored JSON answer schema.

{
  "average_illuminance_lux": <number>,
  "uniformity_ratio_uo": <number>,
  "specific_luminaire_power_density_w_m2_100lux": <number>,
  "target_illuminance_margin_pct": <number>
}
  • average_illuminance_lux · scored within ±3%
  • uniformity_ratio_uo · scored within ±3%
  • specific_luminaire_power_density_w_m2_100lux · scored within ±3%
  • target_illuminance_margin_pct · scored within ±3%