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

Steel Critical Temp

Calculates steel critical temperature from an explicit fire design load ratio using the Eurocode-style relationship theta_cr = 39.19 ln(1/(0.9674 mu^3.833) - 1) + 482. The template reports the critical temperature, margin to a protection trigger, and a numeric protection requirement indicator.

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

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

2 inputs

Always given

Included directly in every task prompt.

2
  • Load ratio

    load_ratio

    Design load effect divided by ambient-temperature resistance

    0.05 – 0.95
  • Protection trigger

    protection_trigger_c

    Critical temperature threshold below which fire protection is required

    350 – 650 C

Scored outputs

3 outputs

Critical temperature c

critical_temperature_c

Critical steel temperature

Scores if within ±3% of the reference value.

Protection margin c

protection_margin_c

Critical temperature minus protection trigger temperature

Scores if within ±3% of the reference value.

Protection required

protection_required

Numeric fire protection requirement 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 low-utilisation member
medium:
All parameters given across low and moderate utilisation members
hard:
All parameters given for moderate and high utilisation members

Task bundle

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

/workspace

  • instruction.md
  • steel-critical-temp_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 structural fire checks.2 3## Problem4 5Calculate the critical steel temperature from the member load ratio and determine whether the critical temperature falls below the fire protection trigger.6 7## Given8 9| Parameter | Value | Unit |10|-----------|-------|------|11| Load ratio mu | {{ load_ratio }} | - |12| Protection trigger temperature | {{ protection_trigger_c }} | C |13 14{% if archetype_description is defined %}15### Structural Fire Context16 17{{ archetype_description }}18{% endif %}19 20{% if tool_available %}21## Available Tool22 23A steel critical temperature calculation tool is available at `/workspace/{{ meta.name }}_calc.py`. Run it with:24 25```bash26python3 /workspace/{{ meta.name }}_calc.py --help27```28 29You may use this tool to verify your calculations or compute values directly.30{% endif %}31 32## Required33 34Calculate the following:35 361. Critical steel temperature (C)372. Protection margin relative to the trigger temperature (C)383. Numeric fire protection requirement indicator: 0 no, 1 yes39 40## Constraints41 42- No internet access is available. Work from engineering knowledge and the provided tool.43- Use theta_cr = 39.19 x ln(1 / (0.9674 x mu^3.833) - 1) + 482.44- Use protection margin = critical temperature - protection trigger temperature.45- Set protection_required to 1 when the critical temperature is below the trigger, otherwise 0.46- Treat the load ratio as an explicit input; do not recalculate section capacity.47 48## Output Format49 50Show 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:51 52```json53{54 "critical_temperature_c": <numeric_value>,55 "protection_margin_c": <numeric_value>,56 "protection_required": <numeric_value>57}58```59 60Write your complete solution to `/workspace/output.md`.61

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.

Low utilisation member

low_utilisation_member

Low-utilisation steel member with reserve ambient capacity

secondary-floor-beamlight-industrial-platform
Parameter ranges
load_ratio
0.15 – 0.35
protection_trigger_c
500 – 620

Moderate utilisation member

moderate_utilisation_member

Moderately utilised steel member in a fire-rated zone

commercial-frame-beamplant-room-support-steel
Parameter ranges
load_ratio
0.35 – 0.65
protection_trigger_c
500 – 620

High utilisation member

high_utilisation_member

Highly utilised steel member with low reserve fire capacity

transfer-girderheavily-loaded-column
Parameter ranges
load_ratio
0.65 – 0.9
protection_trigger_c
450 – 600

Example task

commercial-frame-beam-moderate-utilisation-member-previewhard difficulty, all inputs given.

Moderately utilised steel member in a fire-rated zone. commercial-frame-beam. Required outputs: critical_temperature_c, protection_margin_c, protection_required

The model sees

Scenario context and visible inputs.

load_ratio
0.35 to 0.65
protection_trigger_c
500 to 620 C

Executable tool: steel-critical-temp_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.

{
  "critical_temperature_c": <number>,
  "protection_margin_c": <number>,
  "protection_required": <number>
}
  • critical_temperature_c · scored within ±3%
  • protection_margin_c · scored within ±3%
  • protection_required · scored within ±1%