Benchmark
SWE Atlas - Test Writing
SWE Atlas - Test Writing evaluates a model's ability to author meaningful tests for real-world software projects, measuring how well agents can understand…
- Modality
- text
- Categories
- agents, code
- Openness
- unknown
- Source
- llm_stats
- Reported scores
- 1
Reported scores
llm_stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| MiniMax M3 | MiniMax | 0.3083 | 2026-06-01 | 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.