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

T Squared Hrr

Calculates design fire heat release rate using the t-squared growth model HRR = alpha t^2, with an explicit peak HRR cap. The template reports the unclipped HRR, peak-limited HRR, time to peak, and a numeric cap indicator for deterministic fire safety scenario checks.

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

Standards

ISO/TS 16733SFPE Handbook

Tags

design-firedeterministicfire-safetyheat-release-ratemechanical

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

3 inputs

Always given

Included directly in every task prompt.

3

  • Growth coefficient kw s2

    growth_coefficient_kw_s2

    T-squared fire growth coefficient alpha

    0.001 – 0.2 kW/s^2

  • Time from ignition

    time_from_ignition_s

    Time from ignition

    0 – 1800 s

  • Peak hrr

    peak_hrr_kw

    Peak heat release rate cap

    100 – 20000 kW

Scored outputs

4 outputs

Unclipped hrr

unclipped_hrr_kw

Unclipped t-squared heat release rate

Scores if within ±3% of the reference value.

Hrr at time

hrr_at_time_kw

Heat release rate at time after applying peak cap

Scores if within ±3% of the reference value.

Time to peak s

time_to_peak_s

Time from ignition to reach peak HRR

Scores if within ±3% of the reference value.

Peak limited

peak_limited

Numeric peak-limit indicator: 0 no, 1 yes

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.

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 slow-growth design fire
medium:
All parameters given across slow and medium growth fires
hard:
All parameters given for faster growth or peak-limited fire scenarios

Task bundle

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

/workspace

  • instruction.md
  • t-squared-hrr_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 fire safety engineer specializing in design fire scenarios.2 3## Problem4 5Calculate heat release rate using the t-squared fire growth model and apply the peak HRR cap.6 7## Given8 9| Parameter | Value | Unit |10|-----------|-------|------|11| Growth coefficient alpha | {{ growth_coefficient_kw_s2 }} | kW/s^2 |12| Time from ignition t | {{ time_from_ignition_s }} | s |13| Peak HRR limit | {{ peak_hrr_kw }} | kW |14 15{% if archetype_description is defined %}16### Fire Scenario Context17 18{{ archetype_description }}19{% endif %}20 21{% if tool_available %}22## Available Tool23 24A t-squared HRR calculation tool is available at `/workspace/{{ meta.name }}_calc.py`. Run it with:25 26```bash27python3 /workspace/{{ meta.name }}_calc.py --help28```29 30You may use this tool to verify your calculations or compute values directly.31{% endif %}32 33## Required34 35Calculate the following:36 371. Unclipped t-squared HRR (kW)382. HRR at the specified time after applying the peak limit (kW)393. Time to reach the peak HRR (s)404. Numeric peak-limit indicator: 0 no, 1 yes41 42## Constraints43 44- No internet access is available. Work from engineering knowledge and the provided tool.45- Use HRR_unclipped = alpha x t^2.46- Use HRR_at_time = min(HRR_unclipped, peak HRR).47- Use time_to_peak = sqrt(peak HRR / alpha).48- Set peak_limited to 1 when HRR_unclipped is at or above the peak HRR, otherwise 0.49 50## Output Format51 52Show 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:53 54```json55{56 "unclipped_hrr_kw": <numeric_value>,57 "hrr_at_time_kw": <numeric_value>,58 "time_to_peak_s": <numeric_value>,59 "peak_limited": <numeric_value>60}61```62 63Write your complete solution to `/workspace/output.md`.64

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.

Slow growth fire

slow_growth_fire

Slow-growth design fire for low-combustibility occupancy

office-tenancystation-concourse
Parameter ranges
growth_coefficient_kw_s2
0.002 – 0.006
time_from_ignition_s
120 – 900
peak_hrr_kw
1000 – 6000

Medium growth fire

medium_growth_fire

Medium-growth design fire for mixed fuel load occupancy

retail-tenancyworkshop-area
Parameter ranges
growth_coefficient_kw_s2
0.008 – 0.02
time_from_ignition_s
90 – 700
peak_hrr_kw
2000 – 10000

Fast growth fire

fast_growth_fire

Fast-growth design fire for high fuel load storage or plant areas

warehouse-storageplant-room-fire
Parameter ranges
growth_coefficient_kw_s2
0.04 – 0.12
time_from_ignition_s
60 – 500
peak_hrr_kw
3000 – 20000

Example task

retail-tenancy-medium-growth-fire-preview — hard difficulty, all inputs given.

Medium-growth design fire for mixed fuel load occupancy. retail-tenancy. Required outputs: unclipped_hrr_kw, hrr_at_time_kw, time_to_peak_s, peak_limited

The model sees

Scenario context and visible inputs.

growth_coefficient_kw_s2
0.008 to 0.02 kW/s^2
time_from_ignition_s
90 to 700 s
peak_hrr_kw
2000 to 10000 kW

Executable tool: t-squared-hrr_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.

{
  "unclipped_hrr_kw": <number>,
  "hrr_at_time_kw": <number>,
  "time_to_peak_s": <number>,
  "peak_limited": <number>
}
  • unclipped_hrr_kw · scored within ±3%
  • hrr_at_time_kw · scored within ±3%
  • time_to_peak_s · scored within ±3%
  • peak_limited · scored within ±1%