MiniMax-M2.1 / .eval_results /swe_bench_verified.yaml
SaylorTwift's picture
SaylorTwift HF Staff
Add SWE-bench Verified evaluation result (74.0%)
742e8cc verified
raw
history blame
225 Bytes
- dataset:
id: SWE-bench/SWE-bench_Verified
task_id: swe_bench_%_resolved
value: 74.0
date: '2026-03-17'
source:
url: https://huggingface.co/MiniMaxAI/MiniMax-M2.1
name: Model Card
user: SaylorTwift