Best AI for summarising documents / head-to-head

Claude Sonnet 5 vs DeepSeek V4 Profor summarising documents

The verdict

DeepSeek V4 Pro wins, 9593

Same 12 summarising documents tasks, marked blind by three rival labs. DeepSeek V4 Pro took 3 tasks, Claude Sonnet 5 took 3, 6 tied. Tested 13 Aug 2026.

Where they differed most

The task — One-sentence gist

Reduce to ONE sentence of no more than 25 words: 'After eighteen months of testing across four hospitals, the trial found that the new triage system reduced average waiting times by 22 minutes, although staff reported it added roughly ten minutes of administrative work per shift and two sites abandoned it before the trial ended.'

The 18-month, four-hospital trial found the new triage system cut waits by 22 minutes but added 10 minutes of staff paperwork; two sites quit early.
An 18-month, four-hospital trial found new triage system cut wait times by 22 minutes, but added ten admin minutes per shift and two sites withdrew.

Task by task

TaskClaude Sonnet 5DeepSeek V4 Pro
Meeting notes to actions910
Five-bullet summary1010
Do not invent1010
One-sentence gist108
Preserve the caveat1010
Summarise a disagreement910
Extract the decision510
Long to short, no loss1010
Summary for a specific reader99
Bullet the risks only1010
Headline and standfirst98
Say when there is nothing to summarise109

Full receipts: Claude Sonnet 5, DeepSeek V4 Pro · judges gemini-3.1-pro-preview, gpt-5.6-terra, grok-4.5

Questions people ask

Which is better for summarising documents: Claude Sonnet 5 or DeepSeek V4 Pro?

DeepSeek V4 Pro — it scored 95/100 against 93/100 on our 12-task summarising documents suite, winning 3 tasks to 3 with 6 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 DeepSeek V4 Pro · Claude Opus 4.8 vs Claude Sonnet 5 · DeepSeek V4 Pro vs GPT-5.5 · Claude Sonnet 5 vs GPT-5.5 · DeepSeek V4 Pro vs GPT-5.6 Luna · Claude Sonnet 5 vs GPT-5.6 Luna

Full ranking: Best AI for summarising documents · model pages: Claude Sonnet 5, DeepSeek V4 Pro