Benchmark
SWE-Perf Benchmark
What is SWE-Perf?
Software Engineering Performance benchmark measuring code optimization capabilities. Benchmark Radar tracks 1 reported scores for SWE-Perf, cited by 1 source…
- Modality
- text
- Evaluates
- code
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 1
Source provenance
- Original evidence https://api.zeroeval.com/leaderboard/benchmarks/swe-perf?top_n=500
SWE-Perf results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| MiniMax M2.1 | MiniMax | 0.031 | 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.