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

Detention Volume Preliminary

Estimates the required stormwater detention storage volume using a simplified triangular inflow hydrograph with constant outflow, as commonly applied in preliminary site drainage design per TR-55 and local council requirements. Computes the volume difference between post-development peak inflow and the allowable release rate over the storm duration, and derives an approximate basin surface area from a nominated design depth.

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

Standards

Local requirementsTR-55

Tags

civildetentiondeterministicdrainagehydrologystoragestormwater

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

  • Post dev peak flow

    post_dev_peak_flow_m3_s

    Post-development peak flow rate Q_post

    0.05 – 15 m³/s

  • Storm duration

    storm_duration_hr

    Design storm duration t_storm

    0.5 – 24 hr

  • Design depth

    design_depth_m

    Design water depth of the detention basin

    0.5 – 2 m

Derived from scenario

Sampled from the scenario and inferable from its description.

1

  • Allowable release rate

    allowable_release_rate_m3_s

    Allowable (pre-development or regulated) release rate Q_allow

    Derived from the archetype scenario. Hidden at hard difficulty.

    0.01 – 10 m³/s

Scored outputs

2 outputs

Required storage volume m3

required_storage_volume_m3

Required detention storage volume (m³)

Scores if within ±3% of the reference value.

Approximate surface area m2

approximate_surface_area_m2

Approximate basin surface area at design depth (m²)

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

All parameters given — straightforward volume calculation with clear Q_post > Q_allow

medium

All inputs given

All parameters given but larger flows and longer storms — agent must apply correct case logic

hard

Some inputs hidden

Allowable release rate hidden — agent must infer from site description and local requirements

Hidden inputs

  • Allowable release rateallowable_release_rate_m3_s

Prompt replacement text

The site is a {{ archetype.description }} ({{ archetype.site_context }})

Task bundle

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

/workspace

  • instruction.md
  • detention-volume-preliminary_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 civil engineer specializing in stormwater management and drainage design.2 3## Problem4 5Estimate the required detention basin volume to attenuate post-development peak flow to the allowable release rate, using a simplified triangular hydrograph method.6 7## Given8 9| Parameter | Value | Unit |10|-----------|-------|------|11| Post-development peak flow (Q_post) | {{ post_dev_peak_flow_m3_s }} | m³/s |12{% if allowable_release_rate_m3_s is defined %}13| Allowable release rate (Q_allow) | {{ allowable_release_rate_m3_s }} | m³/s |14{% endif %}15| Design storm duration (t_storm) | {{ storm_duration_hr }} | hr |16| Design water depth | {{ design_depth_m }} | m |17{% if archetype_description is defined %}18 19### Site Conditions20 21{{ archetype_description }}22{% endif %}23 24{% if tool_available %}25## Available Tool26 27A detention volume calculation tool is available at `/workspace/{{ meta.name }}_calc.py`. Run it with:28 29```bash30python3 /workspace/{{ meta.name }}_calc.py --help31```32 33You may use this tool to verify your calculations or compute values directly.34{% endif %}35 36## Required37 38Calculate the following:39 401. Required detention storage volume (m³)412. Approximate basin surface area at design depth (m²)42 43## Applicable Standards44 45- TR-55 — Urban Hydrology for Small Watersheds46- Local council stormwater detention requirements47 48## Constraints49 50- No internet access is available. Work from engineering knowledge and the provided tool.51- Use the simplified triangular hydrograph method:52 - **Triangular inflow hydrograph:** peak = Q_post, base = t_storm53 - Inflow volume = Q_post × t_storm × 3600 / 254 - **Constant outflow** at Q_allow during the storm55 - Outflow volume = Q_allow × t_storm × 360056 - **Required storage volume** depends on the relationship between Q_allow and Q_post:57 - If Q_allow < Q_post/2:58 V = t_storm × 3600 × (Q_post/2 − Q_allow)59 - If Q_allow ≥ Q_post/2:60 V = (Q_post − Q_allow)² × t_storm × 3600 / (2 × Q_post)61 - If Q_allow ≥ Q_post, no detention is needed (V = 0)62 - **Approximate surface area:** A_surface = V / design_depth63- If Q_allow is not given directly, infer a reasonable value from the site description and local detention requirements64 65## Output Format66 67Show your step-by-step working in Markdown, including formulas and intermediate calculations. At the end of your solution, include a JSON block with your final answers in exactly this format:68 69```json70{71 "required_storage_volume_m3": <numeric_value>,72 "approximate_surface_area_m2": <numeric_value>73}74```75 76Write your complete solution to `/workspace/output.md`.77

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 residential subdivision

small_residential_subdivision

Small residential subdivision on gentle terrain with local council detention requirements

sydney-northwest-growth-areamelbourne-casey-corridorbrisbane-north-lakes
Parameter ranges
post_dev_peak_flow_m3_s
0.1 – 1
allowable_release_rate_m3_s
0.05 – 0.5
storm_duration_hr
1 – 6
design_depth_m
0.5 – 1.2

Commercial development

commercial_development

Commercial or mixed-use development with high impervious coverage and moderate catchment

parramatta-cbd-redevelopmentgold-coast-robina-town-centreadelaide-tonsley-innovation
Parameter ranges
post_dev_peak_flow_m3_s
0.5 – 5
allowable_release_rate_m3_s
0.2 – 2
storm_duration_hr
1 – 6
design_depth_m
0.8 – 1.5

Industrial estate

industrial_estate

Industrial estate with large hardstand areas and concentrated runoff

western-sydney-aerotropolisgeelong-northern-industrialtownsville-port-expansion
Parameter ranges
post_dev_peak_flow_m3_s
1 – 8
allowable_release_rate_m3_s
0.3 – 3
storm_duration_hr
1 – 12
design_depth_m
1 – 2

Large greenfield

large_greenfield

Large greenfield development converting rural land to mixed residential with significant flow increase

wollondilly-growth-areagreater-springfield-qldarmstrong-creek-vic
Parameter ranges
post_dev_peak_flow_m3_s
3 – 15
allowable_release_rate_m3_s
1 – 6
storm_duration_hr
2 – 24
design_depth_m
1 – 2

Example task

sydney-northwest-growth-area-small-residential-subdivision-preview — hard difficulty, some inputs hidden.

Small residential subdivision on gentle terrain with local council detention requirements. sydney-northwest-growth-area. Required outputs: required_storage_volume_m3, approximate_surface_area_m2

The model sees

Scenario context and visible inputs.

post_dev_peak_flow_m3_s
0.1 to 1 m³/s
storm_duration_hr
1 to 6 hr
design_depth_m
0.5 to 1.2 m

Executable tool: detention-volume-preliminary_calc.py

The model must infer

Inputs withheld at this difficulty.

  • Allowable release rate

    allowable_release_rate_m3_s

Stand-in text in the prompt

The site is a {{ archetype.description }} ({{ archetype.site_context }})

The model must produce

The scored JSON answer schema.

{
  "required_storage_volume_m3": <number>,
  "approximate_surface_area_m2": <number>
}
  • required_storage_volume_m3 · scored within ±3%
  • approximate_surface_area_m2 · scored within ±3%