Downstream invert
downstream_invert_m
Downstream invert level IL_ds (m AHD)
Scores if within ±3% of the reference value.
Calculates the downstream invert level, obvert (crown) level, cover depth, and grade fall for a stormwater drainage pipe given upstream invert, length, grade, diameter, and downstream surface level. Checks cover adequacy against minimum requirements for the installation context per Australian local-authority stormwater drainage standards.
with-tool: The model is given an executable Python calculator script.
Standards
One template produces many comparable benchmark tasks while keeping the scoring contract fixed.
01
The reusable contract shown on this page.
02
An archetype and site context are sampled.
03
Inputs may be hidden at harder tiers.
04
The model responds with the declared outputs.
Inputs the model receives, and the outputs it is scored on.
6 inputs
Included directly in every task prompt.
Upstream invert m
upstream_invert_m
Upstream invert level IL_us
Pipe length
pipe_length_m
Pipe length between pits L
Pipe grade percent
pipe_grade_percent
Pipe longitudinal grade as a percentage
Pipe diameter
pipe_diameter_mm
Nominal pipe internal diameter D
Surface level ds m
surface_level_ds_m
Surface level at downstream pit
Used only when the sampled task needs this part of the contract.
Minimum cover
minimum_cover_mm
Minimum required cover depth over pipe crown
Derived from the archetype scenario. Optional input. Hidden at hard difficulty.
5 outputs
downstream_invert_m
Downstream invert level IL_ds (m AHD)
Scores if within ±3% of the reference value.
obvert_level_m
Obvert (crown) level at downstream end OL_ds (m AHD)
Scores if within ±3% of the reference value.
cover_depth_mm
Cover depth at downstream end (mm)
Scores if within ±500% of the reference value.
grade_fall_m
Total fall over pipe length (m)
Scores if within ±3% of the reference value.
cover_adequate
Cover adequacy (1.0 = adequate, 0.0 = insufficient)
Scores if within ±1% of the reference value.
Each template is sampled at three tiers. Harder tiers may hide inputs, forcing the model to infer them from the scenario description.
All inputs given
Small pipe under footpath, all parameters given, generous cover
All inputs given
Any pipe size and archetype, all parameters given
Some inputs hidden
Minimum cover hidden, agent must infer from installation context
Hidden inputs
Prompt replacement text
The pipe is {{ archetype.description }} installed at {{ archetype.site_context }}
The exact instruction and parameter contract used to generate this task, pinned to the published library source.
/workspace
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 in Australia.2 3## Problem4 5Calculate the downstream invert level, obvert (crown) level, cover depth, and grade fall for a stormwater drainage pipe. Determine whether the cover depth at the downstream end meets the minimum requirement for the installation context.6 7## Given8 9| Parameter | Value | Unit |10|-----------|-------|------|11| Upstream invert level (IL_us) | {{ upstream_invert_m }} | m AHD |12| Pipe length (L) | {{ pipe_length_m }} | m |13| Pipe grade | {{ pipe_grade_percent }} | % |14| Pipe diameter (D) | {{ pipe_diameter_mm }} | mm |15| Surface level at downstream pit | {{ surface_level_ds_m }} | m AHD |16{%- if minimum_cover_mm is defined %}17| Minimum cover requirement | {{ minimum_cover_mm }} | mm |18{%- endif %}19{%- if archetype_description is defined %}20 21### Installation Context22 23{{ archetype_description }}24{% endif %}25 26{% if tool_available %}27## Available Tool28 29A pipe invert calculation tool is available at `/workspace/pipe-invert-calculation_calc.py`. Run it with:30 31```bash32python3 /workspace/pipe-invert-calculation_calc.py --help33```34 35You may use this tool to verify your calculations or compute values directly.36{% endif %}37 38## Required39 40Calculate the following:41 421. Grade fall over the pipe length (m)432. Downstream invert level IL_ds (m AHD)443. Obvert (crown) level at the downstream end OL_ds (m AHD)454. Cover depth at the downstream end (mm)465. Cover adequacy (1.0 if cover >= minimum requirement, 0.0 if insufficient)47 48## Applicable Standards49 50- AS/NZS 3500.3 — Stormwater drainage51- QUDM Section 7 — Pipe drainage design52 53## Minimum Cover Requirements (Typical Australian Practice)54 55| Installation Context | Minimum Cover (mm) |56|---------------------|-------------------|57| Under road pavement | 600 |58| Under verge or footpath | 450 |59| Under heavy traffic / trunk mains | 600–900 |60 61## Constraints62 63- No internet access is available. Work from engineering knowledge and the provided tool.64- Use the following formulae:65 - **Grade fall:** fall = (grade / 100) × L66 - **Downstream invert:** IL_ds = IL_us − fall67 - **Obvert (crown) level:** OL_ds = IL_ds + D, where D is the diameter in metres (convert from mm)68 - **Cover depth:** cover_mm = (surface_level_ds − OL_ds) × 100069 - **Cover adequacy:** 1.0 if cover_mm ≥ minimum_cover_mm, otherwise 0.070- Round all numerical outputs to 2 decimal places.71 72## Output Format73 74Show your step-by-step working in Markdown, including unit conversions, grade fall, invert calculation, obvert calculation, cover depth, and adequacy check. At the end of your solution, include a JSON block with your final answers in exactly this format:75 76```json77{78 "downstream_invert_m": <numeric_value>,79 "obvert_level_m": <numeric_value>,80 "cover_depth_mm": <numeric_value>,81 "grade_fall_m": <numeric_value>,82 "cover_adequate": <numeric_value>83}84```85 86Write your complete solution to `/workspace/output.md`.87 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.
suburban_road_drainage
PVC stormwater pipe under suburban road pavement
verge_and_footpath
PVC stormwater pipe under grass verge or footpath
trunk_stormwater
Reinforced concrete trunk stormwater main under road reserve
steep_hillside
HDPE or PVC stormwater pipe on steep hillside terrain
brisbane-suburban-road-drainage-suburban-road-drainage-preview — hard difficulty, some inputs hidden.
PVC stormwater pipe under suburban road pavement. brisbane-suburban-road-drainage. Required outputs: downstream_invert_m, obvert_level_m, cover_depth_mm, grade_fall_m, cover_adequate
Scenario context and visible inputs.
Executable tool: pipe-invert-calculation_calc.py
Inputs withheld at this difficulty.
Minimum cover
minimum_cover_mm
Stand-in text in the prompt
The pipe is {{ archetype.description }} installed at {{ archetype.site_context }}
The scored JSON answer schema.
{
"downstream_invert_m": <number>,
"obvert_level_m": <number>,
"cover_depth_mm": <number>,
"grade_fall_m": <number>,
"cover_adequate": <number>
}