SWT-Bench

coding

Software Test Benchmark evaluating LLM ability to write tests for software repositories

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
    69.3%