Best AI for everyday maths / head-to-head
GLM 5.2 vs GPT-5.6 Solfor everyday maths
GPT-5.6 Sol wins, 99–97
Same 12 everyday maths tasks, marked blind by three rival labs. GPT-5.6 Sol took 2 tasks, GLM 5.2 took 1, 9 tied. Tested 14 Aug 2026.
Where they differed most
Roughly how many working hours are there in a UK full-time year? Give your estimate, show the 2-3 assumptions it rests on, and say which assumption moves the answer most.
**Estimate:** Roughly **1,750 working hours** in a UK full-time year. **The 3 Assumptions:** 1. **Standard weekly hours:** The baseline work week is 37.5 hours (a common UK standard, sitting between the 35-hour weeks often seen in the public sector and the 40-hour weeks common in the private sector). 2. **Paid time off:** The worker takes 28 days of paid leave per year. This is the UK statutory minimum (5.6 weeks), which typically includes the 8 public (bank) holidays. This leaves roughly 46.5 working weeks in the year. 3. **Sickness and abs…
**Rough estimate: about 1,740 working hours per year.**
Assumptions:
1. **37.5 paid working hours per week** (7.5 hours × 5 days).
2. **52 weeks per year.**
3. **28 days of paid leave**, including UK bank holidays—equivalent to 5.6 weeks.
Calculation:
\[
(52 - 5.6) \times 37.5 \approx 1,740 \text{ hours}
\]
The assumption that moves the answer most is **weekly contracted hours**. A 40-hour week under the same leave assumption gives about **1,856 hours**, whereas changing annual leave by one week changes the result by only **37.5 hours**.Task by task
| Task | GLM 5.2 | GPT-5.6 Sol |
|---|---|---|
| VAT both ways | 10 | 10 |
| Percentage change vs points | 10 | 10 |
| Unit price comparison | 10 | 10 |
| Mortgage overpayment intuition | 10 | 9 |
| Split a bill with a twist | 10 | 10 |
| Compound vs simple | 10 | 10 |
| The discount stack | 10 | 10 |
| Reverse percentage | 10 | 10 |
| Rate to reality | 10 | 10 |
| Average of averages trap | 10 | 10 |
| Estimate honestly | 8 | 10 |
| Refuse false precision | 8 | 10 |
Full receipts: GLM 5.2, GPT-5.6 Sol · judges claude-sonnet-5, gemini-3.1-pro-preview, gpt-5.6-terra
Questions people ask
Which is better for everyday maths: GLM 5.2 or GPT-5.6 Sol?
GPT-5.6 Sol — it scored 99/100 against 97/100 on our 12-task everyday maths suite, winning 2 tasks to 1 with 9 tied. Every answer was marked blind by three judges from three rival AI labs.
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 Sol · Claude Opus 4.8 vs GLM 5.2 · GPT-5.6 Sol vs GPT-5.6 Terra · Claude Opus 4.6 vs GPT-5.6 Sol · GPT-5.3-Codex vs GPT-5.6 Sol · GPT-5.5 vs GPT-5.6 Sol
Full ranking: Best AI for everyday maths · model pages: GLM 5.2, GPT-5.6 Sol