LIVEdataset aec-bench@releasetasks 552models 18disciplines 5last submission … · built …

civilwith-tool

Bund Volume Calculation

Calculates the required bund containment capacity for oil and hazardous liquid storage as the greater of 110% of the largest container or 25% of total stored volume, per AS/NZS 1940. Accounts for equipment displacement within the bund and checks whether the net available volume meets the regulatory minimum.

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

Standards

AS/NZS 1940

How this task is generated

One template produces many comparable benchmark tasks while keeping the scoring contract fixed.

01
Template
The reusable contract shown on this page.
02
Scenario
An archetype and site context are sampled.
03
Difficulty tier
Inputs may be hidden at harder tiers.
04
Task prompt
The model responds with the declared outputs.

Parameters

Inputs the model receives, and the outputs it is scored on.

Inputs

8 inputs

Always given

Included directly in every task prompt.

Num containers
num_containers
Number of oil-filled containers within the bund
1 – 12
Largest container volume
largest_container_volume_l
Volume of the largest single container
100 – 50000 L
Total stored volume
total_stored_volume_l
Total stored volume across all containers
100 – 200000 L
Bund length
bund_length_m
Internal length of the bund enclosure
1 – 25 m
Bund width
bund_width_m
Internal width of the bund enclosure
1 – 15 m

Derived from scenario

Sampled from the scenario and inferable from its description.

Bund wall height
bund_wall_height_m
Height of the bund containment walls
Derived from the archetype scenario.
0.15 – 1.5 m

Optional

Used only when the sampled task needs this part of the contract.

Num equipment items
num_equipment_items
Number of equipment items inside the bund (pumps, pipework supports, etc.)
Optional input. Hidden at hard difficulty.
0 – 6
Equipment footprint area
equipment_footprint_area_m2
Average footprint area of each equipment item inside the bund
Optional input. Hidden at hard difficulty.
0 – 4 m²

Scored outputs

4 outputs

Required bund volume m3

required_bund_volume_m3

Required bund capacity per AS/NZS 1940 (m³)

Scores if within ±3% of the reference value.

Net bund volume m3

net_bund_volume_m3

Net available bund volume after equipment displacement (m³)

Scores if within ±3% of the reference value.

Bund wall height

bund_wall_height_m

Bund wall height (m)

Scores if within ±3% of the reference value.

Compliance

compliance

Compliance flag: 1.0 if net >= required, 0.0 otherwise

Scores if within ±1% 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

Single container with no equipment displacement — straightforward volume check

Num equipment items restricted to: 0

Equipment footprint area m2 restricted to: 0

medium

All inputs given

Multiple containers with equipment displacement — agent must apply both AS/NZS 1940 rules

hard

Some inputs hidden

Equipment displacement parameters hidden — agent must infer count and footprint from site description

Hidden inputs

Num equipment itemsnum_equipment_items
Equipment footprint area m2equipment_footprint_area_m2

Prompt replacement text

The site is a {{ archetype.description }} ({{ archetype.site_context }}). Determine appropriate equipment displacement from the installation context.

Task bundle

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

/workspace

instruction.md
bund-volume-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 civil engineer specializing in hazardous materials storage and spill containment design.2 3## Problem4 5Calculate the required containment bund volume for an oil storage installation in accordance with AS/NZS 1940 (*The storage and handling of flammable and combustible liquids*).6 7## Given8 9| Parameter | Value | Unit |10|-----------|-------|------|11| Number of containers | {{ num_containers }} | - |12| Largest single container volume | {{ largest_container_volume_l }} | L |13| Total stored volume (all containers) | {{ total_stored_volume_l }} | L |14| Bund internal length | {{ bund_length_m }} | m |15| Bund internal width | {{ bund_width_m }} | m |16{% if bund_wall_height_m is defined %}17| Bund wall height | {{ bund_wall_height_m }} | m |18{% endif %}19{% if num_equipment_items is defined and num_equipment_items|int > 0 %}20| Number of equipment items in bund | {{ num_equipment_items }} | - |21| Average equipment footprint area | {{ equipment_footprint_area_m2 }} | m² |22{% endif %}23{% if archetype_description is defined %}24 25### Site Conditions26 27{{ archetype_description }}28{% endif %}29 30{% if tool_available %}31## Available Tool32 33A bund volume calculation tool is available at `/workspace/{{ meta.name }}_calc.py`. Run it with:34 35```bash36python3 /workspace/{{ meta.name }}_calc.py --help37```38 39You may use this tool to verify your calculations or compute values directly.40{% endif %}41 42## Required43 44Calculate the following:45 461. Required bund capacity per AS/NZS 1940 (m³)472. Net available bund volume after equipment displacement (m³)483. Bund wall height (m)494. Compliance status (1.0 if net volume meets requirement, 0.0 if not)50 51## Applicable Standards52 53- AS/NZS 1940:2017 — The storage and handling of flammable and combustible liquids54 55## Constraints56 57- No internet access is available. Work from engineering knowledge and the provided tool.58- Use the AS/NZS 1940 bund volume method:59  - **Required bund capacity** is the greater of:60    - 110% of the volume of the largest single container61    - 25% of the total stored volume of all containers62  - Convert all volumes from litres to cubic metres (1 m³ = 1000 L)63  - **Gross bund volume:** V_gross = length × width × wall_height64  - **Equipment displacement:** V_equip = num_equipment_items × footprint_area × wall_height65    - Each equipment item is simplified as a rectangular prism extending to the full bund wall height66  - **Net bund volume:** V_net = V_gross − V_equip67  - **Compliance:** V_net ≥ required bund capacity68- Bund wall height must be between 0.15 m and 1.5 m per AS/NZS 1940 practical limits69- If bund wall height is not given directly, select a suitable height based on the installation type and standard practice70 71## Output Format72 73Show 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:74 75```json76{77  "required_bund_volume_m3": <numeric_value>,78  "net_bund_volume_m3": <numeric_value>,79  "bund_wall_height_m": <numeric_value>,80  "compliance": <numeric_value>81}82```83 84Write your complete solution to `/workspace/output.md`.85

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.

Single transformer

single_transformer

Single oil-filled power transformer in a dedicated bund enclosure

sydney-substationbrisbane-zone-substationmelbourne-industrial-park

Parameter ranges

num_containers: 1
largest_container_volume_l: 500 – 5000
total_stored_volume_l: 500 – 5000
bund_length_m: 3 – 8
bund_width_m: 2 – 6
bund_wall_height_m: 0.3 – 0.8
num_equipment_items: 0 – 1
equipment_footprint_area_m2: 0 – 0.5

Fuel storage depot

fuel_storage_depot

Multiple above-ground fuel storage tanks at a bulk fuel depot

perth-kwinana-fuel-depotdarwin-east-arm-terminalgladstone-industrial

Parameter ranges

num_containers: 3 – 8
largest_container_volume_l: 10000 – 50000
total_stored_volume_l: 40000 – 200000
bund_length_m: 10 – 25
bund_width_m: 6 – 15
bund_wall_height_m: 0.5 – 1.5
num_equipment_items: 2 – 6
equipment_footprint_area_m2: 0.5 – 2

Workshop oil store

workshop_oil_store

Small workshop oil and lubricant storage area with drum pallets

cairns-maintenance-depotadelaide-fleet-workshophobart-council-yard

Parameter ranges

num_containers: 4 – 12
largest_container_volume_l: 200 – 1000
total_stored_volume_l: 1000 – 10000
bund_length_m: 2 – 6
bund_width_m: 1.5 – 4
bund_wall_height_m: 0.15 – 0.5
num_equipment_items: 0 – 2
equipment_footprint_area_m2: 0 – 0.3

Generator compound

generator_compound

Diesel generator compound with day tank and bulk storage

townsville-data-centrealice-springs-remote-powergeelong-hospital-backup

Parameter ranges

num_containers: 2 – 4
largest_container_volume_l: 2000 – 15000
total_stored_volume_l: 3000 – 30000
bund_length_m: 4 – 12
bund_width_m: 3 – 8
bund_wall_height_m: 0.3 – 1
num_equipment_items: 1 – 3
equipment_footprint_area_m2: 0.5 – 2.5

Example task

perth-kwinana-fuel-depot-fuel-storage-depot-preview — hard difficulty, some inputs hidden.

Multiple above-ground fuel storage tanks at a bulk fuel depot. perth-kwinana-fuel-depot. Required outputs: required_bund_volume_m3, net_bund_volume_m3, bund_wall_height_m, compliance

The model sees

Scenario context and visible inputs.

num_containers: 3 to 8 -
largest_container_volume_l: 10000 to 50000 L
total_stored_volume_l: 40000 to 200000 L
bund_length_m: 10 to 25 m
bund_width_m: 6 to 15 m
bund_wall_height_m: 0.5 to 1.5 m

Executable tool: bund-volume-calculation_calc.py

The model must infer

Inputs withheld at this difficulty.

Equipment footprint area m2
equipment_footprint_area_m2
Num equipment items
num_equipment_items

Stand-in text in the prompt

The site is a {{ archetype.description }} ({{ archetype.site_context }}). Determine appropriate equipment displacement from the installation context.

The model must produce

The scored JSON answer schema.

{
  "required_bund_volume_m3": <number>,
  "net_bund_volume_m3": <number>,
  "bund_wall_height_m": <number>,
  "compliance": <number>
}

required_bund_volume_m3 · scored within ±3%
net_bund_volume_m3 · scored within ±3%
bund_wall_height_m · scored within ±3%
compliance · scored within ±1%

Bund Volume Calculation

How this task is generated

Template

Scenario

Difficulty tier

Task prompt

Parameters

Inputs

Scored outputs

Required bund volume m3

Net bund volume m3

Bund wall height

Compliance

Difficulty

easy

medium

hard

Task bundle

Scenario archetypes

Single transformer

Fuel storage depot

Workshop oil store

Generator compound

Example task

The model sees

The model must infer

The model must produce