Cardio

Race Time Predictor

Predict finish times across 5K, 10K, half marathon, and marathon from any known race result using Riegel's formula.

Predicted Race Times

Base pace / km

5:00 /km

Base pace / mile

8:03 /mi

Predicted Finish Times

Riegel's formula (T2 = T1 × (D2/D1)^1.06) — longer races get progressively harder per km.

4:48 /km

23:59

10K

5:00 /km

50:00

Half Marathon

5:14 /km

1:50:19

Marathon

5:27 /km

3:50:01

00:003:50:01

Distance	Finish time	Pace /km	Effort Δ
5K (5 km)	23:59	4:48	-4.1%
10K (10 km)	50:00	5:00	0%
Half Marathon (21.1 km)	1:50:19	5:14	+4.6%
Marathon (42.2 km)	3:50:01	5:27	+9%

Formula: Riegel (1977) T2 = T1 × (D2/D1)^1.06. Assumes consistent aerobic fitness across distances.

How to use it

Select your known race distance and enter your finish time precisely — even 30 seconds of error shifts all predictions. Use an official chip time, not a watch start/stop.
Choose your target distances. The predictor uses Riegel's formula (T2 = T1 × (D2/D1)^1.06), which assumes consistent aerobic fitness across distances. It performs best when predicting to distances within 3× of your known race.
Read the difficulty delta column: values above +5% indicate the longer race demands meaningfully more aerobic capacity per km than your baseline. A marathon typically shows +12–15% harder pace than a 5K.
Use predicted pace for training zones, not just race goals. If the calculator says your marathon pace is 5:45/km, that pace is a useful aerobic threshold reference for long runs.
Rerun after each race — your fitness evolves and a fresh data point is always more accurate than extrapolating from a 6-month-old result.

AI Integrations

Contract, discovery endpoints, and developer notes for agent use.

Always available for agents

Tool contract JSON

https://aifithub.io/contracts/race-time-predictor.json

Stable input and output contract for this exact tool.

Human review

People can use the browser page to sense-check outputs and charts, but agents should still execute against the contract and discovery endpoints.

/agent-tools.json - machine-readable tool index.
/llms.txt - human-readable model discovery guide.
/.well-known/webmcp.json - WebMCP capabilities manifest.
/.well-known/ai-plugin.json - plugin-style discovery manifest.

{
  "tool": "race_time_predictor",
  "known_distance_km": 10,
  "known_time_minutes": 50,
  "target_distances_km": [
    5,
    10,
    21.0975,
    42.195
  ]
}

Open tool contract JSON Open AI integrations guide

Expand developer notes

Agent playbook

Resolve Race Time Predictor from /agent-tools.json and open its contract before execution.
Validate inputs against the contract schema instead of scraping labels from the page UI.
Open the browser page only when a person wants to review charts, assumptions, or related tools.

Agent FAQ

Should ChatGPT, Claude, or another agent click through the UI?

No. Start with /agent-tools.json, then follow the tool's contract URL. The page UI is for human review, not parameter discovery.

When do tools show Quick and Advanced?

Every tool opens in Quick Start first. Advanced Controls keeps the same scenario, reveals more assumptions or diagnostics, and every tool keeps AI integrations inline below the instructions.

When should an agent still open the browser page?

Open it when a human wants to sense-check the output, review the chart, or keep exploring related tools after the calculation finishes.

Questions people usually ask

What formula is used?

Riegel's endurance model (1977): T2 = T1 × (D2/D1)^1.06. The 1.06 exponent captures the non-linear fatigue increase with longer distances — you slow down proportionally more as distance increases.

How accurate are these predictions?

Within ±5% for well-trained runners predicting to distances within 3× their baseline. Accuracy drops for first-time marathoners extrapolating from a 5K, or for athletes who are significantly stronger at one distance.

Why does my predicted marathon time seem too slow?

Riegel's formula assumes consistent aerobic fitness across all distances. If you are undertrained for the marathon (short long runs, not enough weekly volume), your actual time will be slower than predicted. The formula models potential, not current race readiness.

Can I use a training run instead of a race?

You can, but add 5–8% to your training time to account for the difference between race effort and a typical training effort. Race results give the most accurate predictions because they represent maximum aerobic output.

Is the tool free and private?

Yes. All calculations are client-side. No data leaves your browser.

Related Resources

Learn the decision before you act

Every link here is tied directly to Race Time Predictor. Use the explanation, formula, examples, and benchmarks to pressure-test the calculator output from first principles.

Browse all 1 resources

How To Use · 1

How To Use

5 STEPS

How to Use Race Time Predictor

Optimize your running strategy with the AI Fit Hub's Race Time Predictor. Learn how to input past race data to forecast future performance for various distances, set realistic goals, and tailor your training plans effectively.

Read