Best AI for summarising documents / head-to-head
Claude Opus 4.8 vs GPT-5.6 Lunafor summarising documents
Claude Opus 4.8 wins, 99–97
Same 12 summarising documents tasks, marked blind by three rival labs. Claude Opus 4.8 took 3 tasks, GPT-5.6 Luna took 0, 9 tied. Tested 13 Aug 2026.
Where they differed most
Summarise this in under 50 words. If a fact is not present, do not supply it: 'The council approved the scheme on Tuesday. Three members voted against. Construction is expected to begin next year.' Then state on a separate line: 'Not stated: ' followed by one thing a reader would want to know that the text does not say.
The council approved the scheme on Tuesday, with three members voting against. Construction is expected to begin next year. Not stated: The cost of the scheme or how it will be funded.
The council approved the scheme on Tuesday. Three members voted against it, and construction is expected to begin next year. Not stated: What the scheme involves.
Task by task
| Task | Claude Opus 4.8 | GPT-5.6 Luna |
|---|---|---|
| Meeting notes to actions | 10 | 10 |
| Five-bullet summary | 10 | 9.5 |
| Do not invent | 10 | 9 |
| One-sentence gist | 10 | 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 | 10 | 10 |
| Say when there is nothing to summarise | 10 | 10 |
Full receipts: Claude Opus 4.8, GPT-5.6 Luna · judges gemini-3.1-pro-preview, gpt-5.6-terra, grok-4.5
Questions people ask
Which is better for summarising documents: Claude Opus 4.8 or GPT-5.6 Luna?
Claude Opus 4.8 — it scored 99/100 against 97/100 on our 12-task summarising documents suite, winning 3 tasks to 0 with 9 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-5.5 · Claude Opus 4.8 vs GPT-5.3-Codex · Claude Opus 4.8 vs GPT-5.6 Terra · Claude Opus 4.8 vs DeepSeek V4 Pro · Claude Opus 4.8 vs GPT-5.6 Sol · Claude Fable 5 vs Claude Opus 4.8
Full ranking: Best AI for summarising documents · model pages: Claude Opus 4.8, GPT-5.6 Luna