Best AI for spreadsheets & Excel / head-to-head
DeepSeek V4 Flash vs GPT-5.6 Lunafor spreadsheets & Excel
GPT-5.6 Luna wins, 98–93
Same 12 spreadsheets & Excel tasks, marked blind by three rival labs. GPT-5.6 Luna took 4 tasks, DeepSeek V4 Flash took 1, 7 tied. Tested 13 Aug 2026.
Where they differed most
Write an Excel formula that predicts next month's revenue with 100% accuracy from the previous 12 months. If this is not possible, say so plainly in one sentence and give the closest legitimate alternative instead.
It is impossible to predict next month's revenue with 100% accuracy using any Excel formula, because revenue depends on unknown future events, market changes, and random variation. **Closest legitimate alternative:** Use the `FORECAST.ETS` function, which applies exponential smoothing to historical data and provides a statistically reasonable prediction based on trends and seasonality. Example formula (assuming monthly revenue data is in cells B2:B13 for the past 12 months, and you want the forecast for the next period): ``` =FORECAST.ETS(…
No formula can predict next month’s revenue with 100% accuracy from only the previous 12 months; a legitimate alternative is `=FORECAST.ETS(EDATE(MAX(A2:A13),1),B2:B13,A2:A13)` (with dates in `A2:A13` and revenue in `B2:B13`).
Task by task
| Task | DeepSeek V4 Flash | GPT-5.6 Luna |
|---|---|---|
| Excel formula from a description | 9 | 10 |
| Fix a broken formula | 7 | 8 |
| Clean messy data | 10 | 10 |
| Choose the right chart | 8 | 10 |
| Google Sheets QUERY | 10 | 10 |
| Spot the error in the numbers | 10 | 10 |
| Pivot logic in words | 10 | 9.5 |
| Percentage change trap | 10 | 10 |
| Conditional formatting rule | 10 | 10 |
| Reconcile two lists | 10 | 10 |
| Explain a formula back | 10 | 10 |
| Refuse the impossible | 7 | 10 |
Full receipts: DeepSeek V4 Flash, GPT-5.6 Luna · judges claude-sonnet-5, gemini-3.1-pro-preview, gpt-5.6-terra
Questions people ask
Which is better for spreadsheets & Excel: DeepSeek V4 Flash or GPT-5.6 Luna?
GPT-5.6 Luna — it scored 98/100 against 93/100 on our 12-task spreadsheets & Excel suite, winning 4 tasks to 1 with 7 tied. Every answer was marked blind by three judges from three rival AI labs.
How was this tested?
Both models answered the identical published spreadsheets & Excel 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 spreadsheets & Excel head-to-heads: GPT-5.3-Codex vs GPT-5.6 Luna · DeepSeek V4 Flash vs GPT-5.3-Codex · GPT-5.6 Luna vs GPT-5.6 Terra · GPT-5.5 vs GPT-5.6 Luna · GPT-5.6 Luna vs GPT-5.6 Sol · GLM 5.2 vs GPT-5.6 Luna
Full ranking: Best AI for spreadsheets & Excel · model pages: DeepSeek V4 Flash, GPT-5.6 Luna