Claude Sonnet 5 vs Kimi K3 for translation

The verdict

Claude Sonnet 5 wins, 9187

Same 12 translation tasks, marked blind by three rival labs. Claude Sonnet 5 took 6 tasks, Kimi K3 took 1, 5 tied. Tested 16 Aug 2026.

Where they differed most

The task — Idioms, not word-for-word

Give the natural French equivalent a French speaker would actually say for each — not literal translations: 1) 'It's raining cats and dogs.' 2) 'That car cost an arm and a leg.' 3) 'I'm feeling a bit under the weather.' 4) 'He let the cat out of the bag.' For each, one line: the French, then the literal back-translation in brackets so the difference is visible.

Voici les équivalents naturels :

1) **Il pleut des cordes.**
(It's raining ropes.)

2) **Cette voiture a coûté les yeux de la tête.**
(That car cost the eyes from the head.)

3) **Je ne suis pas dans mon assiette.**
(I'm not in my plate.)

4) **Il a vendu la mèche.**
(He sold the wick.)
1) Il pleut des cordes. [It's raining ropes.]

2) Cette voiture m'a coûté les yeux de la tête. [That car cost me the eyes of my head.]

3) Je ne suis pas dans mon assiette. [I'm not in my plate.]

4) Il a vendu la mèche. [He sold the wick.]

Worth knowing: for #1 you'd also commonly hear "Il pleut comme vache qui pisse" (vulgar — "like a pissing cow"), and for #2 "Ça coûte un bras" exists too — nearly identical to the English, since "an arm" alone does the job in French.

Task by task

TaskClaude Sonnet 5Kimi K3
Email to French hosts88
The B&B welcome note98
Shop notice, formal German108
French into real English108
Idioms, not word-for-word59
Sie and du109
False friends1010
The pub menu88
Every number survives1010
Firm but polite, auf Deutsch98
Not for a contract1010
Refuse the phishing mailshot108

Full receipts: Claude Sonnet 5, Kimi K3 · judges gemini-3.1-pro-preview, gpt-5.6-terra, grok-4.5

Questions people ask

Which is better for translation: Claude Sonnet 5 or Kimi K3?

Claude Sonnet 5 — it scored 91/100 against 87/100 on our 12-task translation suite, winning 6 tasks to 1 with 5 tied. Every answer was marked blind by three judges from three rival AI labs.

How was this tested?

Both models answered the identical published translation 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 translation head-to-heads: Claude Sonnet 5 vs GPT-5.6 Sol · GPT-5.6 Sol vs Kimi K3 · Claude Sonnet 5 vs GPT-5.6 Luna · GPT-5.6 Luna vs Kimi K3 · Claude Sonnet 5 vs GPT-5.6 Terra · GPT-5.6 Terra vs Kimi K3

Full ranking: Best AI for translation · model pages: Claude Sonnet 5, Kimi K3