Best AI for summarising documents / head-to-head
DeepSeek V4 Pro vs GPT-5.6 Lunafor summarising documents
GPT-5.6 Luna wins, 97–95
Same 12 summarising documents tasks, marked blind by three rival labs. GPT-5.6 Luna took 3 tasks, DeepSeek V4 Pro took 2, 7 tied. Tested 13 Aug 2026.
Where they differed most
Write a headline (max 9 words) and a one-sentence standfirst (max 30 words) for: 'A study of 1,200 UK small businesses found that those which adopted at least one AI tool in 2025 grew revenue 8% faster on average, though the researchers could not establish whether the tools caused the growth or successful firms simply adopt tools sooner.'
**Headline:** AI adopters saw 8% faster revenue growth, study finds **Standfirst:** A study of 1,200 UK small businesses found that those using AI tools in 2025 grew revenue 8% faster on average, but researchers could not prove causation.
**Headline:** AI-using small businesses grew revenue 8% faster in 2025 **Standfirst:** A study of 1,200 UK firms found faster growth among AI adopters, but could not show whether AI drove gains or successful businesses adopted it sooner.
Task by task
| Task | DeepSeek V4 Pro | GPT-5.6 Luna |
|---|---|---|
| Meeting notes to actions | 10 | 10 |
| Five-bullet summary | 10 | 9.5 |
| Do not invent | 10 | 9 |
| One-sentence gist | 8 | 9 |
| Preserve the caveat | 10 | 10 |
| Summarise a disagreement | 10 | 10 |
| Extract the decision | 10 | 10 |
| Long to short, no loss | 10 | 10 |
| Summary for a specific reader | 9 | 9 |
| Bullet the risks only | 10 | 10 |
| Headline and standfirst | 8 | 10 |
| Say when there is nothing to summarise | 9 | 10 |
Full receipts: DeepSeek V4 Pro, GPT-5.6 Luna · judges claude-sonnet-5, gemini-3.1-pro-preview, gpt-5.6-terra
Questions people ask
Which is better for summarising documents: DeepSeek V4 Pro or GPT-5.6 Luna?
GPT-5.6 Luna — it scored 97/100 against 95/100 on our 12-task summarising documents suite, winning 3 tasks to 2 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 summarising documents 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 summarising documents head-to-heads: Claude Opus 4.8 vs GPT-5.6 Luna · Claude Opus 4.8 vs DeepSeek V4 Pro · GPT-5.5 vs GPT-5.6 Luna · DeepSeek V4 Pro vs GPT-5.5 · GPT-5.3-Codex vs GPT-5.6 Luna · GPT-5.6 Luna vs GPT-5.6 Terra
Full ranking: Best AI for summarising documents · model pages: DeepSeek V4 Pro, GPT-5.6 Luna