# Language & multilingual benchmarks > Source: Benchize (https://benchize.com) — https://benchize.com/benchmarks/category/language. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/benchmarks/category/language. Explore Language & multilingual LLM benchmarks and AI model results. Compare source-reported scores with original metrics, evaluation settings and evidence on Benchize. Canonical URL: https://benchize.com/benchmarks/category/language Last updated: 2026-10-21T18:52:20.672Z Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations. Explore language understanding, translation, and multilingual tasks. Compare coverage across languages and check whether an evaluation measures fluency, comprehension, or reasoning in a particular language. Published Oct 21, 2026 ## [MultiNRC](https://benchize.com/benchmarks/scale%3Amultinrc.md) Updated: 10/21/2026 Models tested: 15 Motivated by this gap, we developed the Multilingual Native Reasoning Challenge (MultiNRC), a new multilingual evaluation benchmark that contains native and challenging reasoning… Top models · scale Latest result per model · Version not reported - 1[Muse Spark 1.1](https://benchize.com/models/muse-spark-1-1.md) - 2[Gemini 3.1 Pro Preview](https://benchize.com/models/gemini-3-1-pro-preview.md) - 3[Claude Opus 4.6](https://benchize.com/models/claude-opus-4-6-off.md)Non-thinking View details → ## [Korean](https://benchize.com/benchmarks/scale%3Akorean.md) Updated: 10/21/2026 Models tested: 8 The Scale AI Multilingual Prompts Dataset, composed of 1,000 prompts per language, is tailored to enhance models’ interaction capabilities across multiple languages. This dataset… Top models · scale Latest result per model · Version not reported - 1[GPT-4 Turbo Preview](https://benchize.com/models/gpt-4-turbo-preview.md) - 2[Gemini 2.0 Flash](https://benchize.com/models/gemini-2-0-flash.md) - 3[Claude 3 Sonnet](https://benchize.com/models/claude-3-sonnet.md) View details → ## [Chinese](https://benchize.com/benchmarks/scale%3Achinese.md) Updated: 10/21/2026 Models tested: 5 The Scale AI Multilingual Prompts Dataset, composed of 1,000 prompts per language, is tailored to enhance models’ interaction capabilities across multiple languages. This dataset… Top models · scale Latest result per model · Version not reported - 1[O3 Mini](https://benchize.com/models/o3-mini.md) - 2[DeepSeek R1](https://benchize.com/models/deepseek-r1.md) - 3[Gemini 1.5 Flash](https://benchize.com/models/gemini-1-5-flash.md) View details → ## [Spanish](https://benchize.com/benchmarks/scale%3Aspanish.md) Updated: 10/21/2026 Models tested: 5 The Scale AI Multilingual Prompts Dataset, composed of 1,000 prompts per language, is tailored to enhance models’ interaction capabilities across multiple languages. This dataset… Top models · scale Latest result per model · Version not reported - 1[O3 Mini](https://benchize.com/models/o3-mini.md) - 2[GPT-4 Turbo Preview](https://benchize.com/models/gpt-4-turbo-preview.md) - 3[Gemini 1.5 Flash](https://benchize.com/models/gemini-1-5-flash.md) View details → ## [Japanese](https://benchize.com/benchmarks/scale%3Ajapanese.md) Updated: 10/21/2026 Models tested: 4 The Scale AI Multilingual Prompts Dataset, composed of 1,000 prompts per language, is tailored to enhance models’ interaction capabilities across multiple languages. This dataset… Top models · scale Latest result per model · Version not reported - 1[O3 Mini](https://benchize.com/models/o3-mini.md) - 2[Gemini 1.5 Flash](https://benchize.com/models/gemini-1-5-flash.md) - 3[Gemma 2 27B](https://benchize.com/models/gemma-2-27b-it.md) View details → ## [Arabic](https://benchize.com/benchmarks/scale%3Aarabic.md) Updated: 10/21/2026 Models tested: 4 The Scale AI Multilingual Prompts Dataset, composed of 1,000 prompts per language, is tailored to enhance models’ interaction capabilities across multiple languages. This dataset… Top models · scale Latest result per model · Version not reported - 1[O3 Mini](https://benchize.com/models/o3-mini.md) - 2[Gemini 1.5 Flash](https://benchize.com/models/gemini-1-5-flash.md) - 3[Llama 3.3 70B Instruct](https://benchize.com/models/llama-3-3-70b-instruct.md) View details → ## [Arena text / english](https://benchize.com/benchmarks/lmarena%3Atext%3Aenglish.md) Updated: 10/21/2026 Models tested: 151 Human pairwise preferences on english prompts in Arena’s text evaluation. The original organizer publishes model ratings and uncertainty; these are preference ratings rather than… Top models · Arena Latest result per model · Version not reported - 1[Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High - 2[Claude Opus 5.5](https://benchize.com/models/claude-opus-5-5-high.md)High - 3[Claude Opus 4.6](https://benchize.com/models/claude-opus-4-6-high.md)High View details → ## [Arena text / non english](https://benchize.com/benchmarks/lmarena%3Atext%3Anon_english.md) Updated: 10/21/2026 Models tested: 151 Human pairwise preferences on non english prompts in Arena’s text evaluation. The original organizer publishes model ratings and uncertainty; these are preference ratings rather… Top models · Arena Latest result per model · Version not reported - 1[Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High - 2[Claude Fable 5.1](https://benchize.com/models/claude-fable-5-1-max.md)Max - 3[Claude Opus 5.5](https://benchize.com/models/claude-opus-5-5-high.md)High View details → ## [Arena text style control / english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aenglish.md) Updated: 10/21/2026 Models tested: 151 Human pairwise preferences on english prompts in Arena’s text style control evaluation. The original organizer publishes model ratings and uncertainty, adjusting for response… Top models · Arena Latest result per model · Version not reported - 1[Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High - 2[Muse Wonder](https://benchize.com/models/muse-wonder-max.md)Max - 3[Claude Opus 5.5](https://benchize.com/models/claude-opus-5-5-high.md)High View details → ## [Arena text style control / non english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Anon_english.md) Updated: 10/21/2026 Models tested: 151 Human pairwise preferences on non english prompts in Arena’s text style control evaluation. The original organizer publishes model ratings and uncertainty, adjusting for response… Top models · Arena Latest result per model · Version not reported - 1[Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High - 2[Muse Wonder](https://benchize.com/models/muse-wonder-max.md)Max - 3[Claude Opus 5.5](https://benchize.com/models/claude-opus-5-5-high.md)High View details → ## [Arena text / chinese](https://benchize.com/benchmarks/lmarena%3Atext%3Achinese.md) Updated: 10/21/2026 Models tested: 146 Human pairwise preferences on chinese prompts in Arena’s text evaluation. The original organizer publishes model ratings and uncertainty; these are preference ratings rather than… Top models · Arena Latest result per model · Version not reported - 1[Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High - 2[Claude Fable 5.1](https://benchize.com/models/claude-fable-5-1-max.md)Max - 3[Claude Opus 5.5](https://benchize.com/models/claude-opus-5-5-high.md)High View details → ## [Arena text style control / chinese](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Achinese.md) Updated: 10/21/2026 Models tested: 146 Human pairwise preferences on chinese prompts in Arena’s text style control evaluation. The original organizer publishes model ratings and uncertainty, adjusting for response… Top models · Arena Latest result per model · Version not reported - 1[Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High - 2[Claude Opus 5.5](https://benchize.com/models/claude-opus-5-5-high.md)High - 3[Claude Fable 5.1](https://benchize.com/models/claude-fable-5-1-max.md)Max View details → ## [Arena text / russian](https://benchize.com/benchmarks/lmarena%3Atext%3Arussian.md) Updated: 10/21/2026 Models tested: 150 Human pairwise preferences on russian prompts in Arena’s text evaluation. The original organizer publishes model ratings and uncertainty; these are preference ratings rather than… Top models · Arena Latest result per model · Version not reported - 1[Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High - 2[Muse Wonder](https://benchize.com/models/muse-wonder-max.md)Max - 3[Claude Fable 5.1](https://benchize.com/models/claude-fable-5-1-max.md)Max View details → ## [Arena text style control / russian](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Arussian.md) Updated: 10/21/2026 Models tested: 150 Human pairwise preferences on russian prompts in Arena’s text style control evaluation. The original organizer publishes model ratings and uncertainty, adjusting for response… Top models · Arena Latest result per model · Version not reported - 1[Muse Wonder](https://benchize.com/models/muse-wonder-max.md)Max - 2[Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High - 3[Gemini 3.7 Flash](https://benchize.com/models/gemini-3-7-flash-high.md)High View details → ## [Arena text / french](https://benchize.com/benchmarks/lmarena%3Atext%3Afrench.md) Updated: 10/21/2026 Models tested: 132 Human pairwise preferences on french prompts in Arena’s text evaluation. The original organizer publishes model ratings and uncertainty; these are preference ratings rather than… Top models · Arena Latest result per model · Version not reported - 1[Muse Wonder](https://benchize.com/models/muse-wonder-max.md)Max - 2[Claude Fable 5.1](https://benchize.com/models/claude-fable-5-1-max.md)Max - 3[Claude Opus 5](https://benchize.com/models/claude-opus-5-high.md)High View details → ## [Arena text style control / french](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Afrench.md) Updated: 10/21/2026 Models tested: 132 Human pairwise preferences on french prompts in Arena’s text style control evaluation. The original organizer publishes model ratings and uncertainty, adjusting for response… Top models · Arena Latest result per model · Version not reported - 1[Muse Wonder](https://benchize.com/models/muse-wonder-max.md)Max - 2[Claude Fable 5](https://benchize.com/models/claude-fable-5-high.md)High - 3[Muse Spark 1.3](https://benchize.com/models/muse-spark-1-3-max.md)Max View details → ## [Arena text / spanish](https://benchize.com/benchmarks/lmarena%3Atext%3Aspanish.md) Updated: 10/21/2026 Models tested: 134 Human pairwise preferences on spanish prompts in Arena’s text evaluation. The original organizer publishes model ratings and uncertainty; these are preference ratings rather than… Top models · Arena Latest result per model · Version not reported - 1[Claude Opus 5](https://benchize.com/models/claude-opus-5-max.md)Max - 2[Claude Fable 5.1](https://benchize.com/models/claude-fable-5-1-max.md)Max - 3[Claude Opus 4.6](https://benchize.com/models/claude-opus-4-6.md) View details → ## [Arena text style control / spanish](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aspanish.md) Updated: 10/21/2026 Models tested: 134 Human pairwise preferences on spanish prompts in Arena’s text style control evaluation. The original organizer publishes model ratings and uncertainty, adjusting for response… Top models · Arena Latest result per model · Version not reported - 1[Claude Fable 5](https://benchize.com/models/claude-fable-5-high.md)High - 2[Claude Fable 5.1](https://benchize.com/models/claude-fable-5-1-max.md)Max - 3[Claude Opus 4.6](https://benchize.com/models/claude-opus-4-6.md) View details → ## [Arena text / japanese](https://benchize.com/benchmarks/lmarena%3Atext%3Ajapanese.md) Updated: 10/21/2026 Models tested: 120 Human pairwise preferences on japanese prompts in Arena’s text evaluation. The original organizer publishes model ratings and uncertainty; these are preference ratings rather than… Top models · Arena Latest result per model · Version not reported - 1[Claude Fable 5.1](https://benchize.com/models/claude-fable-5-1-max.md)Max - 2[Claude Opus 5.5](https://benchize.com/models/claude-opus-5-5-high.md)High - 3[Claude Opus 5](https://benchize.com/models/claude-opus-5-max.md)Max View details → ## [Arena text style control / japanese](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ajapanese.md) Updated: 10/21/2026 Models tested: 120 Human pairwise preferences on japanese prompts in Arena’s text style control evaluation. The original organizer publishes model ratings and uncertainty, adjusting for response… Top models · Arena Latest result per model · Version not reported - 1[Claude Fable 5.1](https://benchize.com/models/claude-fable-5-1-max.md)Max - 2[Claude Opus 5.5](https://benchize.com/models/claude-opus-5-5-high.md)High - 3[Claude Fable 5](https://benchize.com/models/claude-fable-5-high.md)High View details → ## [Arena text / korean](https://benchize.com/benchmarks/lmarena%3Atext%3Akorean.md) Updated: 10/21/2026 Models tested: 124 Human pairwise preferences on korean prompts in Arena’s text evaluation. The original organizer publishes model ratings and uncertainty; these are preference ratings rather than… Top models · Arena Latest result per model · Version not reported - 1[Claude Opus 5](https://benchize.com/models/claude-opus-5-max.md)Max - 2[Claude Fable 5.1](https://benchize.com/models/claude-fable-5-1-max.md)Max - 3[Claude Opus 5](https://benchize.com/models/claude-opus-5-high.md)High View details → ## [Arena text style control / korean](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Akorean.md) Updated: 10/21/2026 Models tested: 124 Human pairwise preferences on korean prompts in Arena’s text style control evaluation. The original organizer publishes model ratings and uncertainty, adjusting for response… Top models · Arena Latest result per model · Version not reported - 1[Claude Fable 5.1](https://benchize.com/models/claude-fable-5-1-max.md)Max - 2[Claude Opus 5](https://benchize.com/models/claude-opus-5-max.md)Max - 3[Claude Fable 5](https://benchize.com/models/claude-fable-5-high.md)High View details → ## [Arena text / german](https://benchize.com/benchmarks/lmarena%3Atext%3Agerman.md) Updated: 10/21/2026 Models tested: 129 Human pairwise preferences on german prompts in Arena’s text evaluation. The original organizer publishes model ratings and uncertainty; these are preference ratings rather than… Top models · Arena Latest result per model · Version not reported - 1[Claude Opus 5](https://benchize.com/models/claude-opus-5-max.md)Max - 2[Gemini 3 Pro](https://benchize.com/models/gemini-3-pro.md) - 3[Muse Spark 1.3](https://benchize.com/models/muse-spark-1-3-max.md)Max View details → ## [Arena text style control / german](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Agerman.md) Updated: 10/21/2026 Models tested: 129 Human pairwise preferences on german prompts in Arena’s text style control evaluation. The original organizer publishes model ratings and uncertainty, adjusting for response… Top models · Arena Latest result per model · Version not reported - 1[Gemini 3 Pro](https://benchize.com/models/gemini-3-pro.md) - 2[Muse Spark 1.3](https://benchize.com/models/muse-spark-1-3-max.md)Max - 3[Claude Opus 5](https://benchize.com/models/claude-opus-5-max.md)Max View details → ## [Arena text / polish](https://benchize.com/benchmarks/lmarena%3Atext%3Apolish.md) Updated: 10/21/2026 Models tested: 117 Human pairwise preferences on polish prompts in Arena’s text evaluation. The original organizer publishes model ratings and uncertainty; these are preference ratings rather than… Top models · Arena Latest result per model · Version not reported - 1[Claude Fable 5.1](https://benchize.com/models/claude-fable-5-1-max.md)Max - 2[Claude Opus 5](https://benchize.com/models/claude-opus-5-max.md)Max - 3[Claude Opus 5](https://benchize.com/models/claude-opus-5-high.md)High View details → ## [Arena text style control / polish](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Apolish.md) Updated: 10/21/2026 Models tested: 117 Human pairwise preferences on polish prompts in Arena’s text style control evaluation. The original organizer publishes model ratings and uncertainty, adjusting for response… Top models · Arena Latest result per model · Version not reported - 1[Claude Fable 5.1](https://benchize.com/models/claude-fable-5-1-max.md)Max - 2[Claude Fable 5](https://benchize.com/models/claude-fable-5-high.md)High - 3[Muse Spark 1.1](https://benchize.com/models/muse-spark-1-1.md) View details → ## Methodology and provenance Benchize collects and structures public benchmark reports. Scores, costs, timings, ranks and uncertainty remain attributed to their original sources. Different versions, configurations and measurement units are separate results. Missing fields stay unavailable. --- Cite as: Language & multilingual benchmarks — Benchize, https://benchize.com/benchmarks/category/language (retrieved 2026-10-21)