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

Sabine Rt60

Calculates room reverberation time using the Sabine formula RT60 = 0.161 V / A, where A is the equivalent absorption area. The template uses explicit floor, wall, and ceiling areas and absorption coefficients for a deterministic room acoustics calculation.

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

Standards

ISO 3382

Tags

acousticsdeterministicmechanicalrt60sabine

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

7 inputs

Always given

Included directly in every task prompt.

7
Show 7 inputs

  • Room volume

    room_volume_m3

    Room volume

    10 – 100000 m3

  • Floor area

    floor_area_m2

    Floor surface area

    5 – 10000 m2

  • Floor absorption

    floor_absorption

    Floor absorption coefficient

    0.01 – 1

  • Wall area

    wall_area_m2

    Total wall surface area

    5 – 30000 m2

  • Wall absorption

    wall_absorption

    Wall absorption coefficient

    0.01 – 1

  • Ceiling area

    ceiling_area_m2

    Ceiling surface area

    5 – 10000 m2

  • Ceiling absorption

    ceiling_absorption

    Ceiling absorption coefficient

    0.01 – 1

Scored outputs

3 outputs

Equivalent absorption area m2

equivalent_absorption_area_m2

Equivalent absorption area

Scores if within ±3% of the reference value.

Average absorption coefficient

average_absorption_coefficient

Area-weighted average absorption coefficient

Scores if within ±3% of the reference value.

Rt60 s

rt60_s

Sabine reverberation time

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 small room
medium:
All parameters given across small and large acoustic rooms
hard:
All parameters given for large-volume reverberation checks

Task bundle

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

/workspace

  • instruction.md
  • sabine-rt60_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 room acoustics.2 3## Problem4 5Calculate single-band reverberation time using the Sabine formula.6 7## Given8 9| Parameter | Value | Unit |10|-----------|-------|------|11| Room volume | {{ room_volume_m3 }} | m3 |12| Floor area | {{ floor_area_m2 }} | m2 |13| Floor absorption coefficient | {{ floor_absorption }} | - |14| Wall area | {{ wall_area_m2 }} | m2 |15| Wall absorption coefficient | {{ wall_absorption }} | - |16| Ceiling area | {{ ceiling_area_m2 }} | m2 |17| Ceiling absorption coefficient | {{ ceiling_absorption }} | - |18 19{% if archetype_description is defined %}20### Acoustic Context21 22{{ archetype_description }}23{% endif %}24 25{% if tool_available %}26## Available Tool27 28A Sabine RT60 calculation tool is available at `/workspace/{{ meta.name }}_calc.py`. Run it with:29 30```bash31python3 /workspace/{{ meta.name }}_calc.py --help32```33 34You may use this tool to verify your calculations or compute values directly.35{% endif %}36 37## Required38 39Calculate the following:40 411. Equivalent absorption area (m2)422. Area-weighted average absorption coefficient433. Sabine RT60 (s)44 45## Constraints46 47- No internet access is available. Work from engineering knowledge and the provided tool.48- Use equivalent absorption area A = sum(surface area x absorption coefficient).49- Use average absorption coefficient = A / total surface area.50- Use Sabine reverberation time RT60 = 0.161 x room volume / A.51 52## Output Format53 54Show 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:55 56```json57{58 "equivalent_absorption_area_m2": <numeric_value>,59 "average_absorption_coefficient": <numeric_value>,60 "rt60_s": <numeric_value>61}62```63 64Write your complete solution to `/workspace/output.md`.65

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 meeting room

small_meeting_room

Small meeting room with moderate finishes

office-meeting-roomclinical-consult-room
Parameter ranges
room_volume_m3
40 – 250
floor_area_m2
15 – 80
floor_absorption
0.08 – 0.35
wall_area_m2
40 – 250
wall_absorption
0.05 – 0.25
ceiling_area_m2
15 – 80
ceiling_absorption
0.2 – 0.8

Large hall

large_hall

Large hall or concourse acoustic volume

station-concourseschool-assembly-hall
Parameter ranges
room_volume_m3
1000 – 50000
floor_area_m2
300 – 8000
floor_absorption
0.03 – 0.25
wall_area_m2
600 – 20000
wall_absorption
0.03 – 0.35
ceiling_area_m2
300 – 8000
ceiling_absorption
0.05 – 0.7

Example task

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

Large hall or concourse acoustic volume. station-concourse. Required outputs: equivalent_absorption_area_m2, average_absorption_coefficient, rt60_s

The model sees

Scenario context and visible inputs.

room_volume_m3
1000 to 50000 m3
floor_area_m2
300 to 8000 m2
floor_absorption
0.03 to 0.25
wall_area_m2
600 to 20000 m2
wall_absorption
0.03 to 0.35
ceiling_area_m2
300 to 8000 m2
ceiling_absorption
0.05 to 0.7

Executable tool: sabine-rt60_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.

{
  "equivalent_absorption_area_m2": <number>,
  "average_absorption_coefficient": <number>,
  "rt60_s": <number>
}
  • equivalent_absorption_area_m2 · scored within ±3%
  • average_absorption_coefficient · scored within ±3%
  • rt60_s · scored within ±3%