GLM 5.2 vs GPT-5.5 for bookkeeping

The verdict

GPT-5.5 wins, 9281

Same 12 bookkeeping tasks, marked blind by three rival labs. GPT-5.5 took 8 tasks, GLM 5.2 took 2, 2 tied. Tested 18 Aug 2026.

Where they differed most

The task — Find the £36

A bank reconciliation will not balance. The bank statement closing balance is £8,412.55. The cash book closing balance is £8,376.55. Outstanding items already accounted for: an unpresented cheque of £120.00 and a lodgement of £120.00 not yet on the statement, which cancel each other out. The bookkeeper has checked her additions twice. The cash book receipts for the month, as entered: £451.00, £1,208.30, £96.75, £2,340.00, £415.00, £188.50. The corresponding bank credits: £415.00, £1,208.30, £96.75, £2,340.00, £451.00, £188.50. Work out the difference, say what kind of error it is, explain the arithmetic rule that identifies this class of error at a glance, and say which side is wrong and how she would prove it. Then say what she should do about it in the ledger and what she should NOT do.

**1. The Difference**
The difference between the bank statement closing balance (£8,412.55) and the cash book closing balance (£8,376.55) is **£36.00**. 

**2. Kind of Error**
This is a **transposition error**. Specifically, the figures £451.00 and £415.00 have been transposed. The bookkeeper has entered £451.00 in the cash book where she should have entered £415.00 (or vice versa, but the cash book balance is lower, meaning a receipt is understated or a payment is overstated). 

**3. The Arithmetic Rule**
The rule that identifies this class of…
Adjusted bank statement balance:

- Bank statement closing balance: **£8,412.55**
- Less unpresented cheque: **£120.00**
- Add lodgement not yet credited: **£120.00**

These cancel, so adjusted bank balance remains **£8,412.55**.

Cash book balance: **£8,376.55**

So the difference is:

**£8,412.55 − £8,376.55 = £36.00**

The bank is **£36.00 higher** than the cash book.

This is the classic sign of a **transposition error**: **£451** and **£415** have been interchanged.

Arithmetic rule: a transposition error is usually divisible by **9**. Her…

Task by task

TaskGLM 5.2GPT-5.5
The client lunch and the sandwich109.5
Categorise, and admit what you cannot109
The invoice totals1010
Find the £3638
Profit but no money89
Not your decision to make89
The faded shoebox89
It is my company, it is my money88
The mileage claim810
Capital or revenue810
Quote, invoice, receipt89
Refuse the backdated invoice810

Full receipts: GLM 5.2, GPT-5.5 · judges claude-sonnet-5, gemini-3.1-pro-preview, gpt-5.6-terra

Questions people ask

Which is better for bookkeeping: GLM 5.2 or GPT-5.5?

GPT-5.5 — it scored 92/100 against 81/100 on our 12-task bookkeeping suite, winning 8 tasks to 2 with 2 tied. Every answer was marked blind by three judges from three rival AI labs.

How was this tested?

Both models answered the identical published bookkeeping 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 bookkeeping head-to-heads: GPT-5.5 vs GPT-5.6 Sol · GLM 5.2 vs GPT-5.6 Sol · GPT-5.5 vs Grok 4.5 · GPT-5.5 vs Kimi K3 · Claude Opus 4.8 vs GPT-5.5 · Claude Sonnet 5 vs GPT-5.5

Full ranking: Best AI for bookkeeping · model pages: GLM 5.2, GPT-5.5