File size: 222 Bytes
1825d90 | 1 2 3 4 5 6 7 8 9 | - dataset:
id: SWE-bench/SWE-bench_Verified
task_id: swe_bench_%_resolved
value: 75.80
source:
url: https://www.swebench.com/
name: SWE-Bench official evaluation
user: nielsr
notes: high reasoning |