/best/translationupdated May 202685 models evaluated

Best AI for translation

Translating content across languages while preserving tone and context.

CodingMathWritingResearchTranslationData AnalysisChatbotsStudentsBusinessCreative WritingTabular Data & Spreadsheets

Translation quality is notoriously hard to benchmark — automated metrics (BLEU, COMET) correlate poorly with human judgment on nuanced text. We use FLORES-200 as a ground truth baseline and supplement with human preference scores on literary and technical translation pairs.

What matters: multilingual benchmark depth (how many languages the model was meaningfully trained on), instruction adherence for style constraints (formal vs. informal register, glossary compliance), and long-context coherence for document-level translation. Models trained heavily on English tend to degrade on minority languages.

Our translation rank weights the multilingual benchmark (3×) and instruction-following (1×). If your use case involves a specific language pair, check the underlying FLORES-200 scores directly — aggregate multilingual scores can hide large quality gaps on specific languages.

Full rankings

All 85 models, scored for translation

weighted composite · lower-is-worse
#ModelProviderTask score$/in$/outContext
01Qwen: Qwen3 235B A22B Instruct 2507QQwen5.00/5.0$0.071$0.100262K
02OpenAI: gpt-oss-120bOOpenAI5.00/5.0$0.039$0.180131K
03NVIDIA: Nemotron 3 Nano 30B A3BNNVIDIA5.00/5.0$0.050$0.200262K
04DeepSeek V4 FlashDDeepSeek5.00/5.0$0.100$0.2001.0M
05Qwen: Qwen3 30B A3B Instruct 2507QQwen5.00/5.0$0.090$0.300262K
06Xiaomi: MiMo-V2-FlashXXiaomi5.00/5.0$0.100$0.300262K
07Gemma 4 26B A4B GGoogle5.00/5.0$0.060$0.330262K
08Gemma 4 31BGGoogle5.00/5.0$0.120$0.370262K
09GLM-4.7 FlashZZhipu AI5.00/5.0$0.060$0.400203K
10Gemini 2.5 Flash LiteGGoogle5.00/5.0$0.100$0.4001.0M
11DeepSeek V3.2DDeepSeek5.00/5.0$0.252$0.378131K
12NVIDIA: Nemotron 3 SuperNNVIDIA5.00/5.0$0.090$0.4501M
13Grok 4.1 FastXXAI5.00/5.0$0.200$0.5002M
14DeepSeek V4 ProDDeepSeek5.00/5.0$0.435$0.8701.0M
15Qwen: Qwen3.5-35B-A3BQQwen5.00/5.0$0.139$1.00262K
16Qwen: Qwen3.6 35B A3BQQwen5.00/5.0$0.150$1.00262K
17Qwen: Qwen3.6 FlashQQwen5.00/5.0$0.188$1.131M
18Gemini 3.1 Flash Lite PreviewGGoogle5.00/5.0$0.250$1.501.0M
19Mistral Large 3 2512MMistral5.00/5.0$0.500$1.50262K
20GLM-4.7ZZhipu AI5.00/5.0$0.400$1.75203K
21Qwen: Qwen3.5 Plus 2026-04-20QQwen5.00/5.0$0.300$1.801M
22Qwen: Qwen3.6 PlusQQwen5.00/5.0$0.325$1.951M
23GPT-5 MiniOOpenAI5.00/5.0$0.250$2.00400K
24Qwen: Qwen3.6 27BQQwen5.00/5.0$0.300$2.00262K
25MiMo-V2.5XXiaomi5.00/5.0$0.400$2.001.0M
26R1 0528DDeepSeek5.00/5.0$0.500$2.15164K
27R1DDeepSeek5.00/5.0$0.700$2.50164K
28Grok 4.20XXAI5.00/5.0$1.25$2.502M
29Gemini 3 Flash PreviewGGoogle5.00/5.0$0.500$3.001.0M
30Xiaomi: MiMo-V2-ProXXiaomi5.00/5.0$1.00$3.001.0M
31MoonshotAI: Kimi K2.6MMoonshotAI5.00/5.0$0.730$3.49262K
32GPT-5.4 MiniOOpenAI5.00/5.0$0.750$4.50400K
33o4 MiniOOpenAI5.00/5.0$1.10$4.40200K
34Claude Haiku 4.5AAnthropic5.00/5.0$1.00$5.00200K
35Qwen: Qwen3.6 Max PreviewQQwen5.00/5.0$1.04$6.24262K
36Mistral Medium 3.5MMistral5.00/5.0$1.50$7.50262K
37Qwen 3.7 MaxQQwen5.00/5.0$2.50$7.501M
38GPT-4.1OOpenAI5.00/5.0$2.00$8.001.0M
39o3OOpenAI5.00/5.0$2.00$8.00200K
40Gemini 3.5 FlashGGoogle5.00/5.0$1.50$9.001.0M
41GPT-5OOpenAI5.00/5.0$1.25$10.00400K
42Gemini 2.5 ProGGoogle5.00/5.0$1.25$10.001.0M
43GPT-5.1OOpenAI5.00/5.0$1.25$10.00400K
44Gemini 3.1 Pro PreviewGGoogle5.00/5.0$2.00$12.001.0M
45GPT-5.2OOpenAI5.00/5.0$1.75$14.00400K
46GPT-5.4OOpenAI5.00/5.0$2.50$15.001.1M
47Claude Sonnet 4.6AAnthropic5.00/5.0$3.00$15.001M
48Grok 4XXAI5.00/5.0$3.00$15.00256K
49Grok 3XXAI5.00/5.0$3.00$15.00131K
50Claude Opus 4.6AAnthropic5.00/5.0$5.00$25.001M
51Ministral 3 3B 2512MMistral4.50/5.0$0.100$0.100131K
52Qwen: Qwen3.5-9BQQwen4.50/5.0$0.040$0.150262K
53GPT-5 NanoOOpenAI4.50/5.0$0.050$0.400400K
54GPT-4.1 NanoOOpenAI4.50/5.0$0.100$0.4001.0M
55Grok 3 MiniXXAI4.50/5.0$0.300$0.500131K
56Mistral Small 4MMistral4.50/5.0$0.150$0.600262K
57DeepSeek V3.1DDeepSeek4.50/5.0$0.210$0.790164K
58Codestral 2508MMistral4.50/5.0$0.300$0.900256K
59GPT-5.4 NanoOOpenAI4.50/5.0$0.200$1.25400K
60Google: Gemini 3.1 Flash LiteGGoogle4.50/5.0$0.250$1.501.0M
61GPT-4.1 MiniOOpenAI4.50/5.0$0.400$1.601.0M
62Devstral 2 2512MMistral4.50/5.0$0.400$2.00262K
63Mistral Medium 3.1MMistral4.50/5.0$0.400$2.00131K
64xAI: Grok Build 0.1XXAI4.50/5.0$1.00$2.00256K
65Gemini 2.5 FlashGGoogle4.50/5.0$0.300$2.501.0M
66MiMo-V2.5-ProXXiaomi4.50/5.0$1.00$3.001.0M
67Claude Opus 4.7AAnthropic4.50/5.0$5.00$25.001M
68GPT-5.5OOpenAI4.50/5.0$5.00$30.001.1M
69OpenAI: gpt-oss-20bOOpenAI4.00/5.0$0.030$0.140131K
70Ministral 3 8B 2512MMistral4.00/5.0$0.150$0.150262K
71Mistral Small 3.2 24BMMistral4.00/5.0$0.075$0.200128K
72Ministral 3 14B 2512MMistral4.00/5.0$0.200$0.200262K
73Qwen: Qwen3 Coder 30B A3B InstructQQwen4.00/5.0$0.070$0.270160K
74Llama 4 ScoutMMeta4.00/5.0$0.080$0.30010M
75Devstral Small 1.1MMistral4.00/5.0$0.100$0.300131K
76Llama 3.3 70B InstructMMeta4.00/5.0$0.100$0.320131K
77Llama 4 MaverickMMeta4.00/5.0$0.150$0.6001.0M
78Mistral Small 3.1 24BMMistral4.00/5.0$0.351$0.555128K
79DeepSeek V3.1 TerminusDDeepSeek4.00/5.0$0.270$0.950164K
80Grok Code Fast 1XXAI4.00/5.0$0.200$1.50256K
81Devstral MediumMMistral4.00/5.0$0.400$2.00131K
82Grok 4.3XXAI4.00/5.0$1.25$2.501M
83GPT-4oOOpenAI4.00/5.0$2.50$10.00128K
84GPT-4o-miniOOpenAI3.50/5.0$0.150$0.600128K
85Xiaomi: MiMo-V2-OmniXXiaomi2.50/5.0$0.400$2.00262K

Pricing — top 5 for translation

QQwen: Qwen3 235B A22B Instruct 2507
$0.093/MTok
5.00/5.0
OOpenAI: gpt-oss-120b
$0.145/MTok
5.00/5.0
NNVIDIA: Nemotron 3 Nano 30B A3B
$0.163/MTok
5.00/5.0
DDeepSeek V4 Flash
$0.175/MTok
5.00/5.0
QQwen: Qwen3 30B A3B Instruct 2507
$0.247/MTok
5.00/5.0
modelpicker.aipowered by live benchmark data

The best AI for translation changes every month.

We'll email you when rankings shift, new models hit the top 5, or pricing cuts reshuffle the value leaders.

Get notified when models change
Price drops, new models, benchmark updates. One email per change, no spam.