/best/translationupdated July 2026120 models evaluated
Best AI for translation
Translating content across languages while preserving tone and context.
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 120 models, scored for translation
| # | Model | Provider | Task score | $/in | $/out | Context |
|---|---|---|---|---|---|---|
| 01 | inclusionAI: Ling-2.6-flash | IInclusionai | 5.00/5.0 | $0.010 | $0.030 | 262K |
| 02 | Qwen: Qwen3 235B A22B Instruct 2507 | QQwen | 5.00/5.0 | $0.090 | $0.100 | 262K |
| 03 | DeepSeek V4 Flash | DDeepSeek | 5.00/5.0 | $0.077 | $0.154 | 1.0M |
| 04 | OpenAI: gpt-oss-120b | OOpenAI | 5.00/5.0 | $0.036 | $0.180 | 131K |
| 05 | Qwen: Qwen3 30B A3B Instruct 2507 | QQwen | 5.00/5.0 | $0.048 | $0.193 | 131K |
| 06 | NVIDIA: Nemotron 3 Nano 30B A3B | NNVIDIA | 5.00/5.0 | $0.050 | $0.200 | 262K |
| 07 | MiMo-V2.5 | XXiaomi | 5.00/5.0 | $0.105 | $0.280 | 1.0M |
| 08 | Xiaomi: MiMo-V2-Flash | XXiaomi | 5.00/5.0 | $0.100 | $0.300 | 262K |
| 09 | StepFun: Step 3.5 Flash | SStepfun | 5.00/5.0 | $0.100 | $0.300 | 262K |
| 10 | Gemma 4 26B A4B | GGoogle | 5.00/5.0 | $0.060 | $0.330 | 262K |
| 11 | Gemma 4 31B | GGoogle | 5.00/5.0 | $0.120 | $0.350 | 262K |
| 12 | DeepSeek V3.2 | DDeepSeek | 5.00/5.0 | $0.214 | $0.322 | 131K |
| 13 | GLM-4.7 Flash | ZZhipu AI | 5.00/5.0 | $0.060 | $0.400 | 203K |
| 14 | Gemini 2.5 Flash Lite | GGoogle | 5.00/5.0 | $0.100 | $0.400 | 1.0M |
| 15 | NVIDIA: Nemotron 3 Super | NNVIDIA | 5.00/5.0 | $0.080 | $0.450 | 1M |
| 16 | Grok 4.1 Fast | XXAI | 5.00/5.0 | $0.200 | $0.500 | 2M |
| 17 | inclusionAI: Ling-2.6-1T | IInclusionai | 5.00/5.0 | $0.075 | $0.625 | 262K |
| 18 | Inception: Mercury 2 | IInception | 5.00/5.0 | $0.250 | $0.750 | 128K |
| 19 | Arcee AI: Trinity Large Thinking | AArcee-ai | 5.00/5.0 | $0.250 | $0.800 | 262K |
| 20 | DeepSeek V4 Pro | DDeepSeek | 5.00/5.0 | $0.435 | $0.870 | 1.0M |
| 21 | MiniMax: MiniMax M2.7 | MMinimax | 5.00/5.0 | $0.240 | $0.960 | 205K |
| 22 | Qwen: Qwen3.6 35B A3B | QQwen | 5.00/5.0 | $0.140 | $1.00 | 262K |
| 23 | Qwen: Qwen3.5-35B-A3B | QQwen | 5.00/5.0 | $0.140 | $1.00 | 262K |
| 24 | Nex-N2-Pro | NNex AGI | 5.00/5.0 | $0.250 | $1.00 | 262K |
| 25 | MiniMax: MiniMax M2 | MMinimax | 5.00/5.0 | $0.255 | $1.02 | 205K |
| 26 | Qwen: Qwen3.6 Flash | QQwen | 5.00/5.0 | $0.188 | $1.13 | 1M |
| 27 | StepFun: Step 3.7 Flash | SStepfun | 5.00/5.0 | $0.200 | $1.15 | 256K |
| 28 | MiniMax: MiniMax M3 | MMinimax | 5.00/5.0 | $0.300 | $1.20 | 1.0M |
| 29 | Kwaipilot: KAT-Coder-Pro V2 | KKwaipilot | 5.00/5.0 | $0.300 | $1.20 | 256K |
| 30 | Qwen: Qwen3.7 Plus | QQwen | 5.00/5.0 | $0.320 | $1.28 | 1M |
| 31 | Z.ai: GLM 5.2 | ZZhipu AI | 5.00/5.0 | $0.406 | $1.28 | 1.0M |
| 32 | Gemini 3.1 Flash Lite Preview | GGoogle | 5.00/5.0 | $0.250 | $1.50 | 1.0M |
| 33 | Mistral Large 3 2512 | MMistral | 5.00/5.0 | $0.500 | $1.50 | 262K |
| 34 | GLM-4.7 | ZZhipu AI | 5.00/5.0 | $0.400 | $1.75 | 203K |
| 35 | Qwen: Qwen3.5 Plus 2026-04-20 | QQwen | 5.00/5.0 | $0.300 | $1.80 | 1M |
| 36 | Qwen: Qwen3.6 Plus | QQwen | 5.00/5.0 | $0.325 | $1.95 | 1M |
| 37 | GPT-5 Mini | OOpenAI | 5.00/5.0 | $0.250 | $2.00 | 400K |
| 38 | ByteDance Seed: Seed 1.6 | BBytedance-seed | 5.00/5.0 | $0.250 | $2.00 | 262K |
| 39 | R1 0528 | DDeepSeek | 5.00/5.0 | $0.500 | $2.15 | 164K |
| 40 | NVIDIA: Nemotron 3 Ultra | NNVIDIA | 5.00/5.0 | $0.500 | $2.20 | 1M |
| 41 | Qwen: Qwen3.6 27B | QQwen | 5.00/5.0 | $0.285 | $2.40 | 262K |
| 42 | R1 | DDeepSeek | 5.00/5.0 | $0.700 | $2.50 | 164K |
| 43 | Grok 4.20 | XXAI | 5.00/5.0 | $1.25 | $2.50 | 2M |
| 44 | Gemini 3 Flash Preview | GGoogle | 5.00/5.0 | $0.500 | $3.00 | 1.0M |
| 45 | MoonshotAI: Kimi K2.6 | MMoonshotAI | 5.00/5.0 | $0.660 | $3.41 | 262K |
| 46 | Kimi K2.7 Code | MMoonshot AI | 5.00/5.0 | $0.720 | $3.50 | 262K |
| 47 | Qwen 3.7 Max | QQwen | 5.00/5.0 | $1.25 | $3.75 | 1M |
| 48 | GPT-5.4 Mini | OOpenAI | 5.00/5.0 | $0.750 | $4.50 | 400K |
| 49 | o4 Mini | OOpenAI | 5.00/5.0 | $1.10 | $4.40 | 200K |
| 50 | Claude Haiku 4.5 | AAnthropic | 5.00/5.0 | $1.00 | $5.00 | 200K |
| 51 | OpenAI: GPT-5.6 Luna | OOpenAI | 5.00/5.0 | $1.00 | $6.00 | 1.1M |
| 52 | OpenAI: GPT-5.6 Luna Pro | OOpenAI | 5.00/5.0 | $1.00 | $6.00 | 1.1M |
| 53 | Qwen: Qwen3.6 Max Preview | QQwen | 5.00/5.0 | $1.04 | $6.24 | 262K |
| 54 | Grok 4.5 | XXAI | 5.00/5.0 | $2.00 | $6.00 | 500K |
| 55 | Mistral Medium 3.5 | MMistral | 5.00/5.0 | $1.50 | $7.50 | 262K |
| 56 | GPT-4.1 | OOpenAI | 5.00/5.0 | $2.00 | $8.00 | 1.0M |
| 57 | o3 | OOpenAI | 5.00/5.0 | $2.00 | $8.00 | 200K |
| 58 | Gemini 3.5 Flash | GGoogle | 5.00/5.0 | $1.50 | $9.00 | 1.0M |
| 59 | GPT-5 | OOpenAI | 5.00/5.0 | $1.25 | $10.00 | 400K |
| 60 | Gemini 2.5 Pro | GGoogle | 5.00/5.0 | $1.25 | $10.00 | 1.0M |
| 61 | GPT-5.1 | OOpenAI | 5.00/5.0 | $1.25 | $10.00 | 400K |
| 62 | Anthropic: Claude Sonnet 5 | AAnthropic | 5.00/5.0 | $2.00 | $10.00 | 1M |
| 63 | Gemini 3.1 Pro Preview | GGoogle | 5.00/5.0 | $2.00 | $12.00 | 1.0M |
| 64 | GPT-5.2 | OOpenAI | 5.00/5.0 | $1.75 | $14.00 | 400K |
| 65 | GPT-5.4 | OOpenAI | 5.00/5.0 | $2.50 | $15.00 | 1.1M |
| 66 | OpenAI: GPT-5.6 Terra | OOpenAI | 5.00/5.0 | $2.50 | $15.00 | 1.1M |
| 67 | OpenAI: GPT-5.6 Terra Pro | OOpenAI | 5.00/5.0 | $2.50 | $15.00 | 1.1M |
| 68 | Claude Sonnet 4.6 | AAnthropic | 5.00/5.0 | $3.00 | $15.00 | 1M |
| 69 | Grok 4 | XXAI | 5.00/5.0 | $3.00 | $15.00 | 256K |
| 70 | Grok 3 | XXAI | 5.00/5.0 | $3.00 | $15.00 | 131K |
| 71 | Claude Opus 4.6 | AAnthropic | 5.00/5.0 | $5.00 | $25.00 | 1M |
| 72 | Anthropic: Claude Opus 4.8 | AAnthropic | 5.00/5.0 | $5.00 | $25.00 | 1M |
| 73 | OpenAI: GPT-5.6 Sol | OOpenAI | 5.00/5.0 | $5.00 | $30.00 | 1.1M |
| 74 | OpenAI: GPT-5.6 Sol Pro | OOpenAI | 5.00/5.0 | $5.00 | $30.00 | 1.1M |
| 75 | Anthropic: Claude Opus 4.8 (Fast) | AAnthropic | 5.00/5.0 | $10.00 | $50.00 | 1M |
| 76 | Anthropic: Claude Fable 5 | AAnthropic | 5.00/5.0 | $10.00 | $50.00 | 1M |
| 77 | Ministral 3 3B 2512 | MMistral | 4.50/5.0 | $0.100 | $0.100 | 131K |
| 78 | Poolside: Laguna XS 2.1 | PPoolside | 4.50/5.0 | $0.060 | $0.120 | 262K |
| 79 | Qwen: Qwen3.5-9B | QQwen | 4.50/5.0 | $0.100 | $0.150 | 262K |
| 80 | GPT-5 Nano | OOpenAI | 4.50/5.0 | $0.050 | $0.400 | 400K |
| 81 | ByteDance Seed: Seed-2.0-Mini | BBytedance-seed | 4.50/5.0 | $0.100 | $0.400 | 262K |
| 82 | GPT-4.1 Nano | OOpenAI | 4.50/5.0 | $0.100 | $0.400 | 1.0M |
| 83 | Grok 3 Mini | XXAI | 4.50/5.0 | $0.300 | $0.500 | 131K |
| 84 | Mistral Small 4 | MMistral | 4.50/5.0 | $0.150 | $0.600 | 262K |
| 85 | inclusionAI: Ring-2.6-1T | IInclusionai | 4.50/5.0 | $0.075 | $0.625 | 262K |
| 86 | DeepSeek V3.1 | DDeepSeek | 4.50/5.0 | $0.210 | $0.790 | 164K |
| 87 | Codestral 2508 | MMistral | 4.50/5.0 | $0.300 | $0.900 | 256K |
| 88 | MiMo-V2.5-Pro | XXiaomi | 4.50/5.0 | $0.435 | $0.870 | 1.0M |
| 89 | MiniMax: MiniMax-01 | MMinimax | 4.50/5.0 | $0.200 | $1.10 | 1.0M |
| 90 | MiniMax: MiniMax M2.1 | MMinimax | 4.50/5.0 | $0.300 | $1.20 | 205K |
| 91 | GPT-5.4 Nano | OOpenAI | 4.50/5.0 | $0.200 | $1.25 | 400K |
| 92 | Google: Gemini 3.1 Flash Lite | GGoogle | 4.50/5.0 | $0.250 | $1.50 | 1.0M |
| 93 | GPT-4.1 Mini | OOpenAI | 4.50/5.0 | $0.400 | $1.60 | 1.0M |
| 94 | Devstral 2 2512 | MMistral | 4.50/5.0 | $0.400 | $2.00 | 262K |
| 95 | Mistral Medium 3.1 | MMistral | 4.50/5.0 | $0.400 | $2.00 | 131K |
| 96 | xAI: Grok Build 0.1 | XXAI | 4.50/5.0 | $1.00 | $2.00 | 256K |
| 97 | MiniMax: MiniMax M1 | MMinimax | 4.50/5.0 | $0.400 | $2.20 | 1M |
| 98 | Gemini 2.5 Flash | GGoogle | 4.50/5.0 | $0.300 | $2.50 | 1.0M |
| 99 | Claude Opus 4.7 | AAnthropic | 4.50/5.0 | $5.00 | $25.00 | 1M |
| 100 | GPT-5.5 | OOpenAI | 4.50/5.0 | $5.00 | $30.00 | 1.1M |
| 101 | IBM: Granite 4.1 8B | IIbm-granite | 4.00/5.0 | $0.050 | $0.100 | 131K |
| 102 | OpenAI: gpt-oss-20b | OOpenAI | 4.00/5.0 | $0.030 | $0.140 | 131K |
| 103 | Ministral 3 8B 2512 | MMistral | 4.00/5.0 | $0.150 | $0.150 | 262K |
| 104 | Mistral Small 3.2 24B | MMistral | 4.00/5.0 | $0.075 | $0.200 | 128K |
| 105 | Ministral 3 14B 2512 | MMistral | 4.00/5.0 | $0.200 | $0.200 | 262K |
| 106 | Qwen: Qwen3 Coder 30B A3B Instruct | QQwen | 4.00/5.0 | $0.070 | $0.270 | 160K |
| 107 | Llama 4 Scout | MMeta | 4.00/5.0 | $0.100 | $0.300 | 10M |
| 108 | Llama 3.3 70B Instruct | MMeta | 4.00/5.0 | $0.100 | $0.320 | 131K |
| 109 | Llama 4 Maverick | MMeta | 4.00/5.0 | $0.150 | $0.600 | 1.0M |
| 110 | Mistral Small 3.1 24B | MMistral | 4.00/5.0 | $0.351 | $0.555 | 128K |
| 111 | MiniMax: MiniMax M2.5 | MMinimax | 4.00/5.0 | $0.150 | $0.900 | 205K |
| 112 | DeepSeek V3.1 Terminus | DDeepSeek | 4.00/5.0 | $0.270 | $0.950 | 164K |
| 113 | MiniMax: MiniMax M2-her | MMinimax | 4.00/5.0 | $0.300 | $1.20 | 66K |
| 114 | Grok Code Fast 1 | XXAI | 4.00/5.0 | $0.200 | $1.50 | 256K |
| 115 | ByteDance Seed: Seed-2.0-Lite | BBytedance-seed | 4.00/5.0 | $0.250 | $2.00 | 262K |
| 116 | Grok 4.3 | XXAI | 4.00/5.0 | $1.25 | $2.50 | 1M |
| 117 | GPT-4o | OOpenAI | 4.00/5.0 | $2.50 | $10.00 | 128K |
| 118 | ByteDance Seed: Seed 1.6 Flash | BBytedance-seed | 3.50/5.0 | $0.075 | $0.300 | 262K |
| 119 | GPT-4o-mini | OOpenAI | 3.50/5.0 | $0.150 | $0.600 | 128K |
| 120 | IBM: Granite 4.0 Micro | IIbm-granite | 3.00/5.0 | $0.017 | $0.112 | 131K |
Pricing — top 5 for translation
I
5.00/5.0
Q
5.00/5.0
D
5.00/5.0
O
5.00/5.0
Q
5.00/5.0
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.