Can the AI scale a recipe without dropping a number?
The exact prompt “A pancake recipe for 4 uses 200g flour, 2 large eggs, 300ml milk and 1 tablespoon of sugar. Rewrite the quantities to serve 6.”
- Asked 26 June 2026
- N=3, memory off
- 6 models
- Copilot joined 18 Jul 2026
- graded vs the primary source
All 6 answered correctly, a clean pass on this one.
- Claude Correct Max · paid 3/3 exact ×1.5 scaling (300g flour / 3 eggs / 450ml milk / 1.5 tbsp sugar).
- Gemini Correct Pro · paid 3/3 exact ×1.5.
- Perplexity Correct Free 3/3 exact ×1.5 (run-2 added a useful "1 tbsp + 1.5 tsp" conversion).
- Grok Correct Free · Grok 4.3 Fast 3/3 exact ×1.5.
- ChatGPT Correct Free 1/1 captured = exact ×1.5 (300g / 3 / 450ml / 1.5 tbsp). Runs 2-3 + eq2/eq3 blocked mid-run by an HTTP-431 cookie limit (free tier, partial, same as the finance core).
- Copilot Correct Free · Smart 3/3 exact: the ×1.5 method stated and 300g / 3 eggs / 450ml / 1.5 tbsp landed every run. A simple scaling question, done properly, three times running.
Each row is the verdict from N=3 runs, graded case-by-case against the primary source. A confidently wrong answer is the worst outcome: a wrong answer served as reliable, with no hedge, whether invented outright or a real figure served in the wrong field. Appropriate refusal, when no answer is possible, is not a miss.
Plain arithmetic, the kind anyone might ask while cooking. It is the control case: if a model fumbles multiplying four numbers by 1.5, that tells you something about the harder questions too.
Scale ×1.5 (6/4): 300g flour, 3 eggs, 450ml milk, 1.5 tablespoons sugar. Any other quantity = wrong.
Primary source: Arithmetic: every quantity × 1.5 (to serve 6 instead of 4).
The saved answer behind each grade above, exactly as it came back. Open any one.
ClClaude answered, correct26 Jun 2026
- Run 1
- temporary/incognito chat, memory off
- The everyday battery
A pancake recipe for 4 people uses 200g flour, 2 large eggs, 300ml milk and 1 tablespoon of sugar. Rewrite the ingredient quantities to serve 6 people.
Scaling up by 1.5×:
For 6 people you'll need 300g flour, 3 large eggs, 450ml milk and 1½ tablespoons of sugar.
Saved 26 Jun 2026 as docs/
GeGemini answered, correct26 Jun 2026
- Run 1
- temporary chat, memory off
- The everyday battery
A pancake recipe for 4 people uses 200g flour, 2 large eggs, 300ml milk and 1 tablespoon of sugar. Rewrite the ingredient quantities to serve 6 people.
To scale the recipe from 4 people to 6 people, you need to multiply each ingredient by 1.5 (since 6 ÷ 4 = 1.5).
Here are the updated ingredient quantities for 6 people:
- 300g flour (200g x 1.5) - 3 large eggs (2 x 1.5) - 450ml milk (300ml x 1.5) - 1.5 tablespoons of sugar (1 x 1.5)
Saved 26 Jun 2026 as docs/
PePerplexity answered, correct26 Jun 2026
- Run 1
- incognito chat, memory off
- The everyday battery
A pancake recipe for 4 people uses 200g flour, 2 large eggs, 300ml milk and 1 tablespoon of sugar. Rewrite the ingredient quantities to serve 6 people.
To scale from 4 to 6 people, multiply each ingredient by 6/4 = 1.5.
Flour: 200 × 1.5 = 300 g
Eggs: 2 × 1.5 = 3 large eggs
Milk: 300 × 1.5 = 450 ml
Sugar: 1 × 1.5 = 1.5 tablespoons
So for 6 people, you need 300 g flour, 3 large eggs, 450 ml milk, and 1.5 tablespoons of sugar.
Saved 26 Jun 2026 as docs/
GrGrok answered, correct26 Jun 2026
- Run 1
- private/incognito chat, memory off
- The everyday battery
A pancake recipe for 4 people uses 200g flour, 2 large eggs, 300ml milk and 1 tablespoon of sugar. Rewrite the ingredient quantities to serve 6 people.
**Scaled pancake recipe for 6 people:**
- **Flour**: 300g - **Large eggs**: 3 - **Milk**: 450ml - **Sugar**: 1.5 tablespoons (or 3 teaspoons)
Saved 26 Jun 2026 as docs/
ChChatGPT answered, correct26 Jun 2026
- Run 1
- temporary/incognito chat, memory off
- The everyday battery
A pancake recipe for 4 people uses 200g flour, 2 large eggs, 300ml milk and 1 tablespoon of sugar. Rewrite the ingredient quantities to serve 6 people.
To scale the recipe from 4 people to 6 people, multiply each ingredient by 1.5.
Flour: 200 g × 1.5 = 300 g
Eggs: 2 × 1.5 = 3 large eggs
Milk: 300 ml × 1.5 = 450 ml
Sugar: 1 tbsp × 1.5 = 1½ tablespoons (or 1 tbsp + 1½ tsp)
So for 6 people you'll need: 300 g flour, 3 eggs, 450 ml milk, and 1½ tbsp sugar.
Saved 26 Jun 2026 as docs/
CoCopilot answered, correct18 Jul 2026
- Run 1
- fresh chat via "New chat" button, memory ON per run spec — recorded as-found, not toggled
- Copilot joins the board
A pancake recipe for 4 uses 200g flour, 2 large eggs, 300ml milk and 1 tablespoon of sugar. Rewrite the quantities to serve 6.
Copilot said
To scale the recipe from 4 servings to 6, multiply every ingredient by 6/4 = 1.5. The new quantities are:
Flour — 200g × 1.5 = 300g
Eggs — 2 × 1.5 = 3 large eggs
Milk — 300ml × 1.5 = 450ml
Sugar — 1 tbsp × 1.5 = 1.5 tbsp
So your 6‑serving pancake recipe becomes:
300g flour, 3 large eggs, 450ml milk, 1.5 tbsp sugar.
If you want, I can also help you convert these to cups or scale to any number of servings.
Saved 18 Jul 2026 as docs/
Writing about this? Copy the verified result with attribution. The per-question grades are machine-readable as first-party JSON at /scoreboard/rdri.json (CC BY 4.0).
AI Reliability Scoreboard: Can the AI scale a recipe without dropping a number? Asked (26 June 2026): "A pancake recipe for 4 uses 200g flour, 2 large eggs, 300ml milk and 1 tablespoon of sugar. Rewrite the quantities to serve 6." Correct answer: Arithmetic: every quantity × 1.5 (to serve 6 instead of 4). Result across 6 AI assistants (N=3, memory off; Copilot, joined 18 Jul 2026, memory on as found, disclosed; graded vs the primary source): All 6 answered correctly, a clean pass on this one. Source: https://dixon.ai/scoreboard/q/scaling-a-recipe-arithmetic/, DIXON.AI (CC BY 4.0)
Get the next test in your inbox.
This is one question from the AI Reliability Scoreboard. Confidently Wrong is the fortnightly email: a real case where trusting AI cost someone something, checked against the record, then run again on six assistants to see whether it still happens. The free AI-trust checklist comes with it.
Get the next test →