Benchmark
DeepSwee
A benchmark for evaluating the programming capabilities of large language models.
Timeline (last 90 days)
Oct 8
Mistral Large 4 scored approximately 62% on the real-world software engineering benchmark DeepSwee.
Unverified50%
A benchmark for evaluating the programming capabilities of large language models.
Mistral Large 4 scored approximately 62% on the real-world software engineering benchmark DeepSwee.