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

Interval Calculation

Calculates the average waiting interval between lift arrivals by dividing round-trip time by the number of lifts. The template also reports the number of lift arrivals available in a five-minute assessment period.

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

Standards

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

2 inputs

Always given

Included directly in every task prompt.

1
  • Round trip time

    round_trip_time_s

    Lift round-trip time

    20 – 600 s

Hidden at higher difficulty

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

1
  • Lift count

    lift_count

    Number of lifts in the group

    Hidden at hard difficulty.

    1 – 16

Scored outputs

2 outputs

Interval s

interval_s

Average interval between lift arrivals

Scores if within ±3% of the reference value.

Arrivals per 5min

arrivals_per_5min

Lift arrivals in a five-minute period

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

Small lift group with all values visible

medium

All inputs given

Small or large lift group

hard

Some inputs hidden

Lift count hidden in group context

Hidden inputs

  • Lift countlift_count

Prompt replacement text

Use the lift group size implied by {{ archetype.description }}.

Lift count restricted to: 6

Task bundle

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

/workspace

  • instruction.md
  • interval-calculation_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 vertical transportation engineer calculating lift service interval.2 3## Given4 5| Parameter | Value | Unit |6|-----------|-------|------|7| Round-trip time | {{ round_trip_time_s }} | s |8{% if lift_count is defined %}9| Number of lifts | {{ lift_count }} | count |10{% endif %}11 12## Constraints13 14- Average interval equals round-trip time divided by number of lifts.15- Arrivals per five minutes equals 300 seconds divided by interval.16 17## Output Format18 19Include a JSON block with exactly these keys:20 21```json22{23 "interval_s": <numeric_value>,24 "arrivals_per_5min": <numeric_value>25}26```27 28Write your complete solution to `/workspace/output.md`.29

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.

Small group

small_group

Small lift group in a low- or mid-rise building

low-rise-officeapartment-core
Parameter ranges
round_trip_time_s
60 – 180
lift_count
1 – 4

Large group

large_group

Larger lift group in a commercial building

commercial-towerhospital-core
Parameter ranges
round_trip_time_s
100 – 360
lift_count
4 – 12

Example task

commercial-tower-large-group-previewhard difficulty, some inputs hidden.

Larger lift group in a commercial building. commercial-tower. Required outputs: interval_s, arrivals_per_5min

The model sees

Scenario context and visible inputs.

round_trip_time_s
100 to 360 s

Executable tool: interval-calculation_calc.py

The model must infer

Inputs withheld at this difficulty.

  • Lift count

    lift_count

Stand-in text in the prompt

Use the lift group size implied by {{ archetype.description }}.

The model must produce

The scored JSON answer schema.

{
  "interval_s": <number>,
  "arrivals_per_5min": <number>
}
  • interval_s · scored within ±3%
  • arrivals_per_5min · scored within ±3%