Benchmark
SWT-Bench
Software Test Benchmark evaluating LLM ability to write tests for software repositories
- Modality
- text
- Categories
- code
- Openness
- unknown
- Source
- llm_stats
- Reported scores
- 1
Reported scores
llm_stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| MiniMax M2.1 | MiniMax | 0.693 | 2025-12-23 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.