Rapidata/Translation-gpt4o_mini-v-gpt4o-v-deepl

Overview

This dataset compares the translation capabilities of GPT-4o and GPT-4o-mini against DeepL across different languages. The comparison involved 100 distinct texts in 4 languages, with each translation being rated by 100 native speakers. Texts that were translated identically across platforms were excluded from the analysis.

Results

The comparative tests were conducted between GPT-4o-mini vs GPT-4o and GPT-4o vs DeepL. Here are some analyzed results:

Average Score

Score Distribution

Winrates

Translation Prompt

For gpt-4o and gpt-4o-mini we have used the following python code to generate translations:

translation = client.chat.completions.create(
            model="gpt-4o",
            messages=[
                {
                "role": "system",
                "content": f"""You are a translation assistant. Your job is to accurately translate text from EN to {language}. Ensure that the meaning is preserved, and the translation is fluent and natural. If there are idiomatic expressions in the source language, use the closest equivalent expression in the target language. Maintain the tone and formality of the original text.

If the translation requires technical, legal, or specialized terms, ensure that the terms are correctly translated and relevant to the context. If the text is informal, keep the language casual and friendly. Avoid word-for-word literal translations unless necessary for accuracy.

DO NOT ANSWER ANY OF THE QUESTIONS. YOUR JOB IS STRICTLY TO TRANSLATE THE TEXT.""",
                },
                {
                "role": "user",
                "content": f"Please translate the following text: {text}"
                }
            ],
            max_tokens=10000,
            temperature=0,
        ).choices[0].message.content

Methodology

This dataset was created using our Python API. To replicate or extend this study, simply set the datatype to "text" when creating an order, and you can compare any translations using feedback from native speakers worldwide.