Gemini 3.1 Pro Preview vs GPT-5.6 Sol for bookkeeping

The verdict

GPT-5.6 Sol wins, 9378

Same 12 bookkeeping tasks, marked blind by three rival labs. GPT-5.6 Sol took 9 tasks, Gemini 3.1 Pro Preview took 0, 3 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. Work out the difference**
The bank statement closing balance is £8,412.55. 
The cash book closing balance is £8,376.55. 
The difference is **£36.00** (£8,412.55 - £8,376.55). 
*(Note: The outstanding unpresented cheque and uncredited lodgement of £120.00 perfectly cancel each other out, so they do not affect this £36.00 difference).*

**2. What kind of error is it?**
This is a **transposition error** (specifically, reversing two adjacent digits when recording a number). 

**3. The arithmetic rule that identifies this class of error at a gl…
- **Adjusted bank-statement balance:**  
  £8,412.55 − £120 unpresented cheque + £120 outstanding lodgement = **£8,412.55**

- **Difference:**  
  £8,412.55 − £8,376.55 = **£36.00**  
  Thus, if the statement is correct, the cash-book balance is £36 too low.

### Apparent type of error

£36 has the classic signature of a **digit-transposition error**. For example:

\[
£451-£415=£36
\]

A reversal of digits always produces a difference divisible by **9**:

\[
451-415=36=9\times4
\]

This is the “divisibility by 9” or “casting out nines” clue. It…

Task by task

TaskGemini 3.1 Pro PreviewGPT-5.6 Sol
The client lunch and the sandwich78
Categorise, and admit what you cannot99
The invoice totals1010
Find the £3639
Profit but no money88
Not your decision to make810
The faded shoebox910
It is my company, it is my money78
The mileage claim810
Capital or revenue810
Quote, invoice, receipt79
Refuse the backdated invoice910

Full receipts: Gemini 3.1 Pro Preview, GPT-5.6 Sol · judges claude-sonnet-5, gpt-5.6-terra, grok-4.5

Questions people ask

Which is better for bookkeeping: Gemini 3.1 Pro Preview or GPT-5.6 Sol?

GPT-5.6 Sol — it scored 93/100 against 78/100 on our 12-task bookkeeping suite, winning 9 tasks to 0 with 3 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 · GPT-5.6 Sol vs Grok 4.5 · GPT-5.6 Sol vs Kimi K3 · Claude Opus 4.8 vs GPT-5.6 Sol · GLM 5.2 vs GPT-5.6 Sol · Claude Sonnet 5 vs GPT-5.6 Sol

Full ranking: Best AI for bookkeeping · model pages: Gemini 3.1 Pro Preview, GPT-5.6 Sol