Best AI for everyday maths / head-to-head
GPT-5.6 Luna vs Kimi K3for everyday maths
Dead heat: 98 each
Same 12 everyday maths tasks, marked blind by three rival labs. Tested 14 Aug 2026.
Where they differed most
A car does 42 miles per gallon. Petrol is £1.46/litre. One gallon is 4.546 litres. What does a 260-mile journey cost in fuel, to the nearest 10p? Show each step.
1. **Gallons of petrol used:**
\[
260 \div 42 = 6.1905\text{ gallons}
\]
2. **Convert gallons to litres:**
\[
6.1905 \times 4.546 = 28.1419\text{ litres}
\]
3. **Calculate the fuel cost:**
\[
28.1419 \times £1.46 = £41.087
\]
4. **Round to the nearest 10p:**
\[
\boxed{£41.10}
\]
The journey costs **£41.10 in fuel**.# Fuel Cost Calculation
## Step 1: Work out gallons needed
$$\text{Gallons} = \frac{260 \text{ miles}}{42 \text{ mpg}} = 6.19 \text{ gallons (approx)}$$
## Step 2: Convert gallons to litres
$$6.1905 \times 4.546 = 28.14 \text{ litres (approx)}$$
## Step 3: Work out the cost
$$28.14 \times £1.46 = £41.09 \text{ (approx)}$$
## Step 4: Round to the nearest 10p
$$£41.09 \rightarrow \boxed{£41.10}$$
**The 260-mile journey costs approximately £41.10 in fuel.**Task by task
| Task | GPT-5.6 Luna | Kimi K3 |
|---|---|---|
| VAT both ways | 10 | 10 |
| Percentage change vs points | 10 | 10 |
| Unit price comparison | 10 | 10 |
| Mortgage overpayment intuition | 10 | 10 |
| Split a bill with a twist | 10 | 9 |
| Compound vs simple | 10 | 10 |
| The discount stack | 10 | 10 |
| Reverse percentage | 10 | 10 |
| Rate to reality | 9 | 10 |
| Average of averages trap | 10 | 10 |
| Estimate honestly | 9 | 9 |
| Refuse false precision | 10 | 9 |
Full receipts: GPT-5.6 Luna, Kimi K3 · judges claude-sonnet-5, gemini-3.1-pro-preview, grok-4.5
Questions people ask
Which is better for everyday maths: GPT-5.6 Luna or Kimi K3?
They tied at 98/100 on our everyday maths suite — for this job, pick on price or the product you already use.
How was this tested?
Both models answered the identical published everyday maths tasks. Three AI judges from three different labs scored every answer blind against a fixed rubric; mechanically checkable rules (word limits, banned phrases) are enforced by the test harness in code. The raw outputs and judge verdicts are downloadable.
More everyday maths head-to-heads: Claude Opus 4.8 vs GPT-5.6 Luna · Claude Opus 4.8 vs Kimi K3 · GPT-5.6 Luna vs GPT-5.6 Sol · GPT-5.6 Sol vs Kimi K3 · GPT-5.6 Luna vs GPT-5.6 Terra · GPT-5.6 Terra vs Kimi K3
Full ranking: Best AI for everyday maths · model pages: GPT-5.6 Luna, Kimi K3