GPT-5.3-Codex vs Kimi K3 for book writing
GPT-5.3-Codex wins, 95–90
Same 12 book writing tasks, marked blind by three rival labs. GPT-5.3-Codex took 5 tasks, Kimi K3 took 1, 6 tied. Tested 16 Aug 2026.
Where they differed most
A novel: a 14-year-old girl caring for her alcoholic mother in 1980s Sunderland, where the reader must eventually understand things the girl herself cannot. Recommend first or third person — commit, no hedging — with the reasoning, then write the same short moment both ways so the difference shows on the page: Mum asleep at 4pm, tea not made. Roughly 40-60 words per version.
**Choose third person limited.** For this story, you need a narrow lens *and* a little interpretive space. Close third lets you stay tight to the 14-year-old’s experience while planting details she doesn’t decode (smell, routine, neighbours’ reactions, missed school notes, etc.) so the reader can. First person is powerful, but it locks you harder inside her self-explanations. **Same moment, both ways:** **First person (47 words)** Four o’clock and the kettle’s still cold. Mum’s sprawled on the sofa in her cardigan, one shoe on, one off, mo…
**First person. Present tense. Commit to it completely.** The reasoning: 1. **The irony must be structural, not narrated.** In first person, the gap between what she reports and what she understands is built into every sentence — she supplies the facts, the reader supplies the meaning. In third person, the surplus knowledge has to live somewhere, and it lives in the narrator, which means it's *handed* to the reader rather than discovered. Discovery implicates. Delivery merely informs. 2. **It puts the reader in her position.** She's a child…
Task by task
| Task | GPT-5.3-Codex | Kimi K3 |
|---|---|---|
| Is it a book? | 10 | 10 |
| Twelve chapters, one year | 10 | 10 |
| Back cover, no spoilers | 10 | 9 |
| Three cuts that matter | 10 | 10 |
| 70,000 words around a day job | 9 | 8 |
| Unstick the dialogue | 10 | 10 |
| First or third? | 10 | 8 |
| The 30,000-word wall | 9 | 10 |
| Self-publish or chase agents | 9 | 9 |
| The query letter | 8 | 6 |
| Naming the real people | 9 | 9 |
| Refuse the fake memoir | 10 | 9 |
Full receipts: GPT-5.3-Codex, Kimi K3 · judges claude-sonnet-5, gemini-3.1-pro-preview, grok-4.5
Questions people ask
Which is better for book writing: GPT-5.3-Codex or Kimi K3?
GPT-5.3-Codex — it scored 95/100 against 90/100 on our 12-task book writing suite, winning 5 tasks to 1 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 book writing 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 book writing head-to-heads: GPT-5.3-Codex vs GPT-5.6 Sol · GPT-5.6 Sol vs Kimi K3 · GPT-5.3-Codex vs GPT-5.5 · GPT-5.5 vs Kimi K3 · GPT-5.3-Codex vs GPT-5.6 Terra · GPT-5.6 Terra vs Kimi K3
Full ranking: Best AI for book writing · model pages: GPT-5.3-Codex, Kimi K3