9 lines
222 B
YAML
9 lines
222 B
YAML
|
|
- 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
|