Best AI for everyday maths / head-to-head

GLM 5.2 vs GPT-5.6 Lunafor everyday maths

The verdict

GPT-5.6 Luna wins, 9897

Same 12 everyday maths tasks, marked blind by three rival labs. GPT-5.6 Luna took 2 tasks, GLM 5.2 took 1, 9 tied. Tested 14 Aug 2026.

Where they differed most

The task — Refuse false precision

Someone asks: 'Exactly how much will my £10,000 ISA be worth in 10 years?' Answer in under 80 words: explain why no exact figure exists, then give a defensible range with the growth assumptions stated.

No exact figure exists because ISA returns fluctuate based on unpredictable market conditions, interest rates, and whether you hold cash or stocks. 

Assuming no further contributions, a defensible range is **£13,400 to £17,900**:
* **£13,400:** Assumes a Cash ISA averaging 3% annual interest.
* **£17,900:** Assumes a Stocks & Shares ISA averaging 6% annual growth.
No exact figure exists: it depends on whether it’s a cash or investment ISA, future interest/market returns, fees, and withdrawals. As an illustration, assuming no further contributions or withdrawals and annual **net nominal growth of 0%–7%**, £10,000 could become approximately **£10,000–£19,672** after 10 years (compounded annually). This is not a forecast or guarantee; investments could also fall in value.

Task by task

TaskGLM 5.2GPT-5.6 Luna
VAT both ways1010
Percentage change vs points1010
Unit price comparison1010
Mortgage overpayment intuition1010
Split a bill with a twist1010
Compound vs simple1010
The discount stack1010
Reverse percentage1010
Rate to reality109
Average of averages trap1010
Estimate honestly89
Refuse false precision810

Full receipts: GLM 5.2, GPT-5.6 Luna · 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 Luna?

GPT-5.6 Luna — it scored 98/100 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 Luna · Claude Opus 4.8 vs GLM 5.2 · GPT-5.6 Luna vs GPT-5.6 Sol · GLM 5.2 vs GPT-5.6 Sol · GPT-5.6 Luna vs GPT-5.6 Terra · GLM 5.2 vs GPT-5.6 Terra

Full ranking: Best AI for everyday maths · model pages: GLM 5.2, GPT-5.6 Luna