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

civilwith-tool

Hgl Check

Computes the hydraulic grade line (HGL) at the upstream pit of a single stormwater pipe reach using Manning's equation for friction loss and a pit loss coefficient for junction losses. Checks whether the HGL remains below the pit surface level with adequate clearance to prevent surcharging, following ARR 2019 and local council DCP methods.

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

Standards

ARR 2019 Local Council DCPs QUDM

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.

Design flow m3 per s
design_flow_m3_per_s
Design peak flow Q at the pipe reach
0.01 – 4 m³/s
Pipe diameter
pipe_diameter_mm
Nominal internal pipe diameter DN
225300375450525600750900+2
Pipe length
pipe_length_m
Pipe reach length L between pits
10 – 150 m
Tailwater level m
tailwater_level_m
HGL at the downstream pit (tailwater condition)
2 – 30 m AHD
Surface level m
surface_level_m
Surface level at the upstream pit
4 – 35 m AHD

Derived from scenario

Sampled from the scenario and inferable from its description.

Mannings n
mannings_n
Manning's roughness coefficient n for the pipe material
Derived from the archetype scenario. Hidden at hard difficulty.
0.009 – 0.025
Pit loss coefficient
pit_loss_coefficient
Pit/junction loss coefficient K (dimensionless)
Derived from the archetype scenario. Hidden at hard difficulty.
0 – 5

Optional

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

Minimum clearance
minimum_clearance_mm
Minimum required clearance between HGL and surface level
Optional input.
50 – 500 mm

Scored outputs

7 outputs

Flow velocity m per s

flow_velocity_m_per_s

Pipe flow velocity V (m/s)

Scores if within ±3% of the reference value.

Friction loss

friction_loss_m

Friction head loss h_f through the pipe (m)

Scores if within ±3% of the reference value.

Pit loss

pit_loss_m

Pit/junction head loss h_pit (m)

Scores if within ±3% of the reference value.

Hgl upstream

hgl_upstream_m

HGL elevation at the upstream pit (m AHD)

Scores if within ±3% of the reference value.

Clearance

clearance_mm

Clearance between surface level and HGL (mm), positive = below surface

Scores if within ±1000% of the reference value.

Surcharge ratio

surcharge_ratio

HGL to surface level ratio (> 1.0 indicates surcharging)

Scores if within ±3% of the reference value.

Pass fail

pass_fail

Surcharge compliance (1.0 = pass, clearance adequate; 0.0 = fail)

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

Small pipe, straight pit, all parameters given including Manning's n and pit loss K

Pipe diameter restricted to: 225, 300, 375, 450

medium

All inputs given

Any pipe size and pit configuration, all parameters given

hard

Some inputs hidden

Manning's n and pit loss K hidden, agent must infer from pipe material and junction description

Hidden inputs

Mannings nmannings_n
Pit loss coefficientpit_loss_coefficient

Prompt replacement text

The pipe is {{ archetype.description }} installed at {{ 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
hgl-check_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 drainage design and hydraulic analysis.2 3## Problem4 5Perform a hydraulic grade line (HGL) check for a single stormwater pipe reach between two pits. Determine whether the HGL at the upstream pit remains below the pit surface level with adequate clearance to prevent surcharging.6 7## Given8 9| Parameter | Value | Unit |10|-----------|-------|------|11| Design flow (Q) | {{ design_flow_m3_per_s }} | m³/s |12| Pipe diameter (DN) | {{ pipe_diameter_mm }} | mm |13| Pipe length (L) | {{ pipe_length_m }} | m |14{% if mannings_n is defined %}15| Manning's n | {{ mannings_n }} | - |16{% endif %}17{% if pit_loss_coefficient is defined %}18| Pit loss coefficient (K) | {{ pit_loss_coefficient }} | - |19{% endif %}20| Tailwater level (HGL downstream) | {{ tailwater_level_m }} | m AHD |21| Surface level at upstream pit | {{ surface_level_m }} | m AHD |22{% if minimum_clearance_mm is defined %}23| Minimum required clearance | {{ minimum_clearance_mm }} | mm |24{% endif %}25{% if archetype_description is defined %}26 27### Pipe and Pit Conditions28 29{{ archetype_description }}30{% endif %}31 32{% if tool_available %}33## Available Tool34 35A hydraulic grade line calculation tool is available at `/workspace/{{ meta.name }}_calc.py`. Run it with:36 37```bash38python3 /workspace/{{ meta.name }}_calc.py --help39```40 41You may use this tool to verify your calculations or compute values directly.42{% endif %}43 44## Required45 46Calculate the following for the pipe reach:47 481. Flow velocity V in the pipe (m/s)492. Friction head loss h_f through the pipe (m)503. Pit/junction head loss h_pit at the upstream pit (m)514. HGL elevation at the upstream pit (m AHD)525. Clearance between surface level and HGL (mm)536. Surcharge ratio (HGL / surface level)547. Pass/fail assessment (pass if clearance >= minimum clearance)55 56## Applicable Standards57 58- ARR 2019: Australian Rainfall and Runoff59- QUDM: Queensland Urban Drainage Manual60- Local Council Development Control Plans (DCPs)61 62## Constraints63 64- No internet access is available. Work from engineering knowledge and the provided tool.65- Assume the pipe is flowing full (pressure flow assumption for HGL check).66- Use Manning's equation (SI units) for friction loss:67  - **Pipe area:** A = pi x D² / 468  - **Hydraulic radius (full pipe):** R = D / 469  - **Flow velocity:** V = Q / A70  - **Friction slope:** S_f = (V x n / R^(2/3))²71  - **Friction loss:** h_f = S_f x L72- Use the standard minor loss equation for pit losses:73  - **Pit loss:** h_pit = K x V² / (2g), where g = 9.81 m/s²74- **HGL at upstream pit:** HGL_up = HGL_down + h_f + h_pit75- **Clearance:** clearance = (surface_level - HGL_up) x 1000 (in mm)76- **Surcharge ratio:** surcharge_ratio = HGL_up / surface_level77- **Pass/fail:** pass (1.0) if clearance >= minimum clearance, fail (0.0) otherwise78{% if minimum_clearance_mm is not defined %}79- If minimum clearance is not specified, use 150 mm as the default threshold.80{% endif %}81 82## Output Format83 84Show 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:85 86```json87{88  "flow_velocity_m_per_s": <numeric_value>,89  "friction_loss_m": <numeric_value>,90  "pit_loss_m": <numeric_value>,91  "hgl_upstream_m": <numeric_value>,92  "clearance_mm": <numeric_value>,93  "surcharge_ratio": <numeric_value>,94  "pass_fail": <numeric_value>95}96```97 98Write your complete solution to `/workspace/output.md`.99

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.

Concrete pipe straight

concrete_pipe_straight

Reinforced concrete pipe through a straight-through pit with benched invert

brisbane-suburban-drainagesydney-greenfield-subdivision

Parameter ranges

mannings_n: 0.011 – 0.015
pit_loss_coefficient: 0.1 – 0.5
pipe_diameter_mm: 300, 375, 450, 525, 600, 750
design_flow_m3_per_s: 0.03 – 0.21
pipe_length_m: 20 – 80
tailwater_level_m: 8 – 14
surface_level_m: 16 – 20
minimum_clearance_mm: 100 – 300

Concrete pipe bend

concrete_pipe_bend

Reinforced concrete pipe through a pit with a change in direction

melbourne-trunk-stormwateradelaide-urban-renewal

Parameter ranges

mannings_n: 0.011 – 0.015
pit_loss_coefficient: 0.5 – 2.5
pipe_diameter_mm: 375, 450, 600, 750, 900
design_flow_m3_per_s: 0.05 – 0.33
pipe_length_m: 20 – 100
tailwater_level_m: 6 – 12
surface_level_m: 14 – 18
minimum_clearance_mm: 100 – 300

Pvc pipe residential

pvc_pipe_residential

PVC pipe in a residential inter-allotment drainage pit

perth-residential-estategold-coast-infill-development

Parameter ranges

mannings_n: 0.009 – 0.011
pit_loss_coefficient: 0.1 – 0.5
pipe_diameter_mm: 225, 300, 375
design_flow_m3_per_s: 0.01 – 0.12
pipe_length_m: 10 – 50
tailwater_level_m: 4 – 8
surface_level_m: 10 – 14
minimum_clearance_mm: 100 – 200

Large trunk main

large_trunk_main

Large reinforced concrete trunk main through a junction pit with multiple inlets

sydney-trunk-stormwaterbrisbane-creek-diversion

Parameter ranges

mannings_n: 0.012 – 0.015
pit_loss_coefficient: 1 – 5
pipe_diameter_mm: 750, 900, 1050, 1200
design_flow_m3_per_s: 0.2 – 1.3
pipe_length_m: 30 – 150
tailwater_level_m: 3 – 10
surface_level_m: 12 – 18
minimum_clearance_mm: 150 – 500

Example task

brisbane-suburban-drainage-concrete-pipe-straight-preview — hard difficulty, some inputs hidden.

Reinforced concrete pipe through a straight-through pit with benched invert. brisbane-suburban-drainage. Required outputs: flow_velocity_m_per_s, friction_loss_m, pit_loss_m, hgl_upstream_m, clearance_mm, surcharge_ratio

The model sees

Scenario context and visible inputs.

design_flow_m3_per_s: 0.03 to 0.21 m³/s
pipe_diameter_mm: 300 mm
pipe_length_m: 20 to 80 m
tailwater_level_m: 8 to 14 m AHD
surface_level_m: 16 to 20 m AHD
minimum_clearance_mm: 100 to 300 mm

Executable tool: hgl-check_calc.py

The model must infer

Inputs withheld at this difficulty.

Mannings n
mannings_n
Pit loss coefficient
pit_loss_coefficient

Stand-in text in the prompt

The pipe is {{ archetype.description }} installed at {{ archetype.site_context }}

The model must produce

The scored JSON answer schema.

{
  "flow_velocity_m_per_s": <number>,
  "friction_loss_m": <number>,
  "pit_loss_m": <number>,
  "hgl_upstream_m": <number>,
  "clearance_mm": <number>,
  "surcharge_ratio": <number>,
  "pass_fail": <number>
}

flow_velocity_m_per_s · scored within ±3%
friction_loss_m · scored within ±3%
pit_loss_m · scored within ±3%
hgl_upstream_m · scored within ±3%
clearance_mm · scored within ±1000%
surcharge_ratio · scored within ±3%
pass_fail · scored within ±1%

Hgl Check

How this task is generated

Template

Scenario

Difficulty tier

Task prompt

Parameters

Inputs

Scored outputs

Flow velocity m per s

Friction loss

Pit loss

Hgl upstream

Clearance

Surcharge ratio

Pass fail

Difficulty

easy

medium

hard

Task bundle

Scenario archetypes

Concrete pipe straight

Concrete pipe bend

Pvc pipe residential

Large trunk main

Example task

The model sees

The model must infer

The model must produce