Wikibench

Codegolf v2.2

coding

Multilingual: no

Codegolf v2.2 benchmark

Methodology

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

Leaderboard

Showing 4 of 4 results

  1. Gemma 3n E4B Instructed self-reported llm-stats
    16.8%
  2. Gemma 3n E4B Instructed LiteRT Preview self-reported llm-stats
    16.8%
  3. Gemma 3n E2B Instructed self-reported llm-stats
    11.0%
  4. Gemma 3n E2B Instructed LiteRT (Preview) self-reported llm-stats
    11.0%