Accuracy, published

These are the real numbers from Renzy's scanner against an open dataset. No marketing — just MAE, MAPE and RMSE refreshed weekly.

MAPE on kcal

125.5%

Mean absolute percentage error on total calories.

MAE on kcal

261

Mean absolute error. Lower is better.

MAPE on grams

142.5%

Portion estimation is the bottleneck.

How it's computed

Each dataset entry is a real-plate photo with weight measured on a kitchen scale and calories reconstructed from USDA. We run the production pipeline exactly like a user scan — no shortcuts, no extra context, no cache.

Open dataset: each photo + ground-truth is documented at /api/admin/accuracy-dataset.
Identical pipeline to production: vision → garnish filter → sauce + brand override → scale anchor → critique → USDA → confirm drink.
Standard metrics: MAPE, MAE, RMSE. No outlier filtering — the worst cases also appear on this page.
Re-run weekly automatically. If a model iteration regresses, you'll see it here before we do.

Error distribution

From the dataset's plates, this is the distribution of percent error on kcal. The tighter the bars cluster on the left, the better.

0–5%

5–10%

10–20%

20–30%

30–50%

50%+

The 5 worst cases

What we got most wrong in this batch. Publishing them forces us to fix them in the next iteration.

1 croqueta de pollo 25g

Truth: 80 kcal · Predicted: 648 kcal

Error: 710.0%

Café con leche taza 200ml

Truth: 60 kcal · Predicted: 360 kcal

Error: 500.0%

1 taza de arroz blanco cocido

Truth: 206 kcal · Predicted: 884 kcal

Error: 329.1%

1 porción pizza margherita

Truth: 270 kcal · Predicted: 1000 kcal

Error: 270.4%

Patatas medianas (McDonald's)

Truth: 337 kcal · Predicted: 1162 kcal

Error: 244.8%

Last run: 6/22/2026, 6:34:37 AM

Sample size: 27 platos

Model: anthropic/claude-opus-4.7

Batch: cron-2026-06-22-mqou646r

Want to replicate the benchmark with your own dataset? Email us at hola@renzy.app.