Languages

Results per language: the quality level reached, the solutions that reach it, and the language tiers.

Takeaways for , , , and

Takeaway 1

We classify languages by the translation quality we can achieve.

For each quality level, the tier of a language follows from what we measure in it: whether we can assess its quality, how many solutions meet the requirements of the level and whether one-step solutions are enough. For each language and level, we also report the cost of the cheapest solution that meets those requirements and the time of the fastest one.

We record how much training data a language has as a descriptive attribute, and it plays no part in the classification. In a low-resource language that is not grammatically complex, for example one without gender forms or complex formality patterns, accurate translation may be easier to reach. Fewer than two solutions meet the Advanced requirements in 15 of the 40 high-resource languages, such as French, Russian and European Spanish, while two or more meet them in 7 low-resource languages, such as Cebuano, Kyrgyz and Mongolian.

Takeaway 2

We measure the cost, time and complexity needed for two solutions per language to meet each set of quality requirements.

We seek a main solution and a backup. Two solutions meet the requirements in 79 of the 100 languages for Basic, in 78 for Standard and in 53 for Advanced, and in 18 languages we cannot assess all the requirements. For each language and level, we also report the errors per 1,000 words of the best solution.

We implement the candidate solutions in Intento Language Hub and compare the quality, cost and time needed to meet the requirements in each language.

See details → · Explore interactively →

Languages by the number of solutions meeting each set of requirements

Quality levelBasic Standard Advanced Custom

Two or more solutionsOne solutionNo solutionCannot assess

On each language: ★ for each solution that meets the selected requirements, the total errors per 1,000 words (EPT) of the best of them across all requirements, the seconds per 1,000 words of the fastest and the cost per million characters of the cheapest. Where no solution meets the selected requirements, the values of the best available solution.

Amharic★★8.9 EPT321 sec$1,043/1M

Armenian★★7.3 EPT254 sec$556/1M

Assamese★★9.9 EPT292 sec$979/1M

Azerbaijani★★15.2 EPT74 sec$7.78/1M

Basque★★7.9 EPT209 sec$574/1M

Belarusian★★6.6 EPT181 sec$77/1M

Bengali★★6.6 EPT144 sec$12/1M

Bulgarian★★7.3 EPT116 sec$4.94/1M

Catalan★★9.2 EPT68 sec$4.52/1M

Cebuano★★11.2 EPT293 sec$604/1M

Chinese Simplified★★13.2 EPT238 sec$589/1M

Chinese Traditional★★11.2 EPT172 sec$490/1M

Croatian★★4.6 EPT172 sec$45/1M

Danish★★12.2 EPT25 sec$4.09/1M

Dutch★★2.6 EPT56 sec$9.66/1M

Estonian★★5.6 EPT202 sec$607/1M

Farsi★★12.5 EPT68 sec$4.41/1M

Finnish★★13.2 EPT67 sec$7.60/1M

Galician★★10.5 EPT35 sec$7.20/1M

Georgian★★16.2 EPT120 sec$12/1M

German★★8.6 EPT94 sec$4.02/1M

Greek★★2.6 EPT249 sec$47/1M

Hungarian★★12.5 EPT147 sec$33/1M

Icelandic★★10.5 EPT237 sec$47/1M

Indonesian★★12.5 EPT12 sec$0.38/1M

Irish★★8.6 EPT141 sec$951/1M

Japanese★★10.9 EPT191 sec$645/1M

Kannada★★6.3 EPT280 sec$948/1M

Kazakh★★8.9 EPT108 sec$11/1M

Khmer★★7.3 EPT432 sec$27/1M

Korean★★9.9 EPT293 sec$577/1M

Kyrgyz★★7.6 EPT196 sec$553/1M

Lao★★15.2 EPT163 sec$28/1M

Malay★★9.6 EPT13 sec$0.40/1M

Malayalam★★9.9 EPT213 sec$28/1M

Marathi★★5.9 EPT277 sec$902/1M

Mongolian★★9.9 EPT325 sec$609/1M

Norwegian★★9.9 EPT50 sec$10/1M

Odia (Oriya)★★11.5 EPT360 sec$1,054/1M

Slovak★★4.0 EPT108 sec$4.90/1M

Swahili★★8.2 EPT119 sec$543/1M

Swedish★★13.8 EPT41 sec$4.23/1M

Tagalog★★7.6 EPT216 sec$566/1M

Tajik★★7.3 EPT271 sec$577/1M

Tamil★★10.5 EPT200 sec$9.10/1M

Tatar★★7.9 EPT255 sec$645/1M

Telugu★★5.6 EPT273 sec$929/1M

Thai★★9.2 EPT180 sec$554/1M

Turkish★★10.9 EPT45 sec$10/1M

Ukrainian★★5.9 EPT94 sec$20/1M

Uzbek★★5.6 EPT223 sec$38/1M

Vietnamese★★12.5 EPT67 sec$17/1M

Welsh★★8.9 EPT108 sec$4.87/1M

Afrikaans★18.1 EPT203 sec$968/1M

Bosnian★6.3 EPT267 sec$993/1M

Frisian★14.2 EPT301 sec$964/1M

Gujarati★15.2 EPT200 sec$29/1M

Hindi★4.3 EPT228 sec$1,045/1M

Italian★12.2 EPT118 sec$38/1M

Latvian★12.5 EPT274 sec$972/1M

Lithuanian★11.9 EPT359 sec$1,051/1M

Macedonian★12.2 EPT64 sec$13/1M

Nepali★17.1 EPT118 sec$11/1M

Pashto★13.2 EPT403 sec$1,071/1M

Portuguese (European)★14.2 EPT104 sec$72/1M

Punjabi★14.8 EPT679 sec$1,000/1M

Romanian★4.0 EPT216 sec$1,029/1M

Russian★14.2 EPT201 sec$29/1M

Serbian★9.2 EPT225 sec$1,034/1M

Slovenian★14.2 EPT192 sec$49/1M

Spanish (European)★6.3 EPT24 sec$3.92/1M

Albanian17.2 EPT158 sec$63/1M

Arabic (MSA)8.9 EPT239 sec$1,047/1M

Burmese11.5 EPT730 sec$1,132/1M

Czech6.2 EPT232 sec$1,032/1M

French17.2 EPT192 sec$995/1M

Hebrew18.2 EPT300 sec$919/1M

Polish7.1 EPT197 sec$900/1M

Sinhala7.9 EPT147 sec$926/1M

Sundanese21.4 EPT243 sec$636/1M

Urdu5.0 EPT303 sec$991/1M

Yiddish10.5 EPT440 sec$1,116/1M

Haitian Creolecannot assess

Hausacannot assess

Igbocannot assess

Javanesecannot assess

Kinyarwandacannot assess

Kurdish (Kurmanji)cannot assess

Malagasycannot assess

Maltesecannot assess

Scottish Gaeliccannot assess

Takeaway 3

We assign four language tiers based on whether two solutions meet the requirements and how many steps they need.

We aim to get at least two solutions that meet all the requirements of the level (a main solution and a backup). In tier 1, at least two one-step solutions meet them.

In tier 2, at least two meet them only as two-step solutions (translation + post-edit), three-step solutions (translation + LQA + repair) or, for gender neutrality, as solutions with the gender-neutrality agent.

In tier 3, fewer than two solutions meet them after every step we added. Tier 4 holds the languages where the automatic metrics or Intento LQA cannot assess quality.

See details → · Explore interactively →

Errors, cost and time by language tier, for each quality level

In each cell: the languages of the tier, and over them the median total errors per 1,000 words (EPT) of the best solution across all requirements, the median seconds per 1,000 words of the fastest and the median cost per million characters of the cheapest, with the distance to the 25th and 75th percentiles in small type. Where no solution meets the selected requirements, the values of the best available solution.

Tier 1: one-step solutionsTier 2: complex solutionsTier 3: no reliable high qualityTier 4: cannot assessBasic requirements

41 languages16.5 EPT+7.2−3.155 sec+20−31$4.61/1M+$2.84−$1.15

38 languages11.0 EPT+2.1−2.9178 sec+79−59$546/1M+$32−$522

3 languages19.1 EPT+1.1−3.3243 sec+215−20$636/1M+$23−$37

18 languagescannot assess

Standard requirements

20 languages16.1 EPT+6.7−3.649 sec+15−24$4.50/1M+$0.98−$0.49

58 languages13.0 EPT+4.2−3.6137 sec+71−63$30/1M+$537−$21

4 languages16.8 EPT+2.9−2.8262 sec+117−29$599/1M+$48−$37

18 languagescannot assess

Advanced requirements

6 languages11.6 EPT+0.9−1.435 sec+14−19$7.10/1M+$3.26−$5.78

47 languages8.9 EPT+1.8−2.0191 sec+63−80$47/1M+$549−$37

29 languages12.2 EPT+2.6−4.3225 sec+76−33$968/1M+$64−$905

18 languagescannot assess

Takeaway 4

Two one-step solutions meet the Basic requirements in 41 of 82 languages, Standard in 20 and Advanced in 6.

Only Danish, Indonesian, Malay, Norwegian, Turkish and Vietnamese are in tier 1 for all three levels, and 29 languages are in tier 2 for all three. Of the 29 languages in tier 3 for Advanced, 27 are gendered or natural gender languages, and in Burmese and Sundanese no solution meets general translation quality (no critical error, at most three major errors and at most 20 weighted errors per 1,000 words).

See details →

Languages by tier, for each quality level

Takeaway 5

General translation quality is the main factor in the language tiers for Standard requirements.

A solution meets general translation quality with no critical error, at most three major errors and at most 20 weighted errors per 1,000 words. In the languages of tier 1 for Basic, 31% of the one-step LLM solutions meet general translation quality, against 4% in tier 2, while 91% meet tone of voice in both. Tier 1 for Standard holds the languages where several one-step solutions meet general translation quality (four at the median), because the same solution has to meet all the other Standard requirements too.

See details →

One-step LLM solutions meeting each Standard requirement, by language tier

Takeaway 6

The cheapest solution meeting Standard requirements costs a median of ~$5 per million characters in tier 1 and ~$550 where three steps are needed.

In tier 2 where two-step solutions are enough, the cheapest qualifying solution costs a median of ~$8 per million source characters. In each of these groups, the best solution has ~10 errors per 1,000 words at the median. In a three-step solution (translation + LQA + repair), the LQA step makes up ~96% of the cost, and we estimate it from the token counts of its requests at list prices. The fastest solution takes ~50 seconds per 1,000 words with one step and ~180 with three steps.

See details →

Cost per million characters, by language tier

Takeaway 7

General translation quality and gender neutrality account for most differences in language tiers.

The exceptions are tags in Korean and tone of voice in Cebuano and Sundanese, where two solutions meet the requirement only with more steps. For gender neutrality alone, both best solutions are gender-neutral without the gender-neutrality agent in 30 of the 82 languages and with it in 27, while in 25 gendered or natural gender languages fewer than two are. For general translation quality alone (no critical error, at most three major errors and at most 20 weighted errors per 1,000 words), the tiers are those of the Basic level.

Language tiers for each requirement taken alone

Takeaway 8

No low-resource language has two one-step solutions meeting Basic requirements, and 11 of 40 high-resource languages also need more steps.

They are Chinese Simplified and Traditional, Estonian, Finnish, French, Hebrew, Hungarian, Japanese, Korean, Latvian and Thai. Languages of one family often share a tier: all 12 Slavic languages are in tier 1 for Basic, and the Dravidian languages (Kannada, Malayalam, Tamil, Telugu) and the Uralic languages (Estonian, Finnish, Hungarian) are in tier 2 at every level. All 18 languages we cannot assess are low-resource or medium-resource languages.

Language tiers for the Basic requirements, by resource level

Takeaway 9

In 13 languages, full gender neutrality requires rewording because forms of address or verb agreement have no neutral alternative.

In Hindi, Urdu, Punjabi and Gujarati, the verb agrees with the gender of the person, also with the polite form of you. In Croatian, Serbian, Bosnian, Slovenian, Czech, Polish and Lithuanian, past-tense forms and participles carry gender after the polite you or the authorial we. In Arabic and Hebrew, all forms of address are masculine or feminine. We assess these languages against the same gender rule as every other language, and in 12 of them at most one of the two best solutions is fully gender-neutral.

Takeaway 10

Among the languages compared with the 2025 edition, Ukrainian and European Spanish have the lowest one-step error rate in 2026.

Translations into Ukrainian from Anthropic Claude Fable 5 have 9.9 weighted errors per 1,000 words, as do translations into European Spanish from OpenAI GPT-5.6 Terra, and three one-step solutions meet general translation quality (no critical error, at most three major errors and at most 20 weighted errors per 1,000 words) in each of the two languages. In Chinese, French, Japanese and Korean, the best one-step solutions have 21 to 23 weighted errors per 1,000 words, just above that limit.

In the 2025 edition, we translated other texts against other requirements, into Latin American Spanish and Brazilian Portuguese rather than European Spanish and Portuguese.

Takeaway 11

Translation length ranges from ~33% of the English source in Chinese to ~125% in Scottish Gaelic.

A translation has more characters than the English source in 78 of the 100 languages. We count characters without markup, as the median over the translations of the four texts from the 57 models.

Length of a translation against the English source, by language

Takeaway 12

The 2026 list covers 540 languages across 62 MT systems, 21 more languages than the normalized 2025 list.

They are 55 commercial MT vendors and 7 research models still available, such as NLLB-200 and OPUS-MT, with 217,688 language pairs together. The previous edition listed 549 languages, with some languages under several codes, such as Bokmål and Nynorsk for Norwegian. With one code per language, as we count now, that list has 519 languages.

See details → · Explore interactively →

Languages per MT system, 2026 against 2025

Takeaway 13

Only one MT system offers 214 of the 540 languages and 68.5% of language pairs.

English is offered by 59 of the 62 systems, French by 49, Spanish and Russian by 48. NiuTrans alone offers 128,447 pairs that no other system offers, 59% of all pairs. Each of our 100 languages is offered by at least 9 systems, 24 at the median, with Frisian, Uyghur and Wolof the least offered. The other 439 languages are offered by 2 systems at the median. If you need a language offered by one system, you have no second system for a backup.

See details →

Languages by the number of MT systems that offer them

Languages

Takeaways for , , , and

We classify languages by the translation quality we can achieve.

We measure the cost, time and complexity needed for two solutions per language to meet each set of quality requirements.

We assign four language tiers based on whether two solutions meet the requirements and how many steps they need.

Two one-step solutions meet the Basic requirements in 41 of 82 languages, Standard in 20 and Advanced in 6.

General translation quality is the main factor in the language tiers for Standard requirements.

The cheapest solution meeting Standard requirements costs a median of ~$5 per million characters in tier 1 and ~$550 where three steps are needed.

General translation quality and gender neutrality account for most differences in language tiers.

No low-resource language has two one-step solutions meeting Basic requirements, and 11 of 40 high-resource languages also need more steps.

In 13 languages, full gender neutrality requires rewording because forms of address or verb agreement have no neutral alternative.

Among the languages compared with the 2025 edition, Ukrainian and European Spanish have the lowest one-step error rate in 2026.

Translation length ranges from ~33% of the English source in Chinese to ~125% in Scottish Gaelic.

The 2026 list covers 540 languages across 62 MT systems, 21 more languages than the normalized 2025 list.

Only one MT system offers 214 of the 540 languages and 68.5% of language pairs.

More on Languages

Automate translation to meet your requirements

Languages

Takeaways for Localization managers, Business leaders, Linguists, and other rolesLocalization engineersLSPsTech vendors (TMS / MT)AI labs / model buildersAnalysts / pressProcurementAcademics──────────See everything

We classify languages by the translation quality we can achieve.

We measure the cost, time and complexity needed for two solutions per language to meet each set of quality requirements.

We assign four language tiers based on whether two solutions meet the requirements and how many steps they need.

Two one-step solutions meet the Basic requirements in 41 of 82 languages, Standard in 20 and Advanced in 6.

General translation quality is the main factor in the language tiers for Standard requirements.

The cheapest solution meeting Standard requirements costs a median of ~$5 per million characters in tier 1 and ~$550 where three steps are needed.

General translation quality and gender neutrality account for most differences in language tiers.

No low-resource language has two one-step solutions meeting Basic requirements, and 11 of 40 high-resource languages also need more steps.

In 13 languages, full gender neutrality requires rewording because forms of address or verb agreement have no neutral alternative.

Among the languages compared with the 2025 edition, Ukrainian and European Spanish have the lowest one-step error rate in 2026.

Translation length ranges from ~33% of the English source in Chinese to ~125% in Scottish Gaelic.

The 2026 list covers 540 languages across 62 MT systems, 21 more languages than the normalized 2025 list.

Only one MT system offers 214 of the 540 languages and 68.5% of language pairs.

More on Languages

Automate translation to meet your requirements

Takeaways for , , , and