Wikibench

ECLeKTic

reasoning official site →

Multilingual: no

A multilingual closed-book question answering dataset that evaluates cross-lingual knowledge transfer in large language models across 12 languages, using knowledge-seeking questions based on Wikipedia articles that exist only in one language

Methodology

Imported from llm-stats public benchmark metadata. Modality: text. Max score: 1. Categories: language, reasoning. Language: en. Verified by llm-stats: no.

Leaderboard

Showing 8 of 8 results

  1. Gemma 3n E4B Instructed self-reported llm-stats
    19.0%
  2. Gemma 3 27B self-reported llm-stats
    16.7%
  3. Gemma 3 12B self-reported llm-stats
    10.3%
  4. Gemma 3 4B self-reported llm-stats
    4.6%
  5. Gemma 3n E2B Instructed self-reported llm-stats
    2.5%
  6. Gemma 3n E2B Instructed LiteRT (Preview) self-reported llm-stats
    2.5%
  7. Gemma 3n E4B Instructed LiteRT Preview self-reported llm-stats
    1.9%
  8. Gemma 3 1B self-reported llm-stats
    1.4%