OctoCodingBench

coding

Octopus coding benchmark for evaluating multi-language programming capabilities

Methodology

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

Leaderboard

  1. MiniMax M2.1 self-reported llm-stats
    26.1%