Add SWE-Bench Verified evaluation results
#1
by
nielsr HF Staff - opened
.eval_results/swe_bench_verified.yaml
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
- dataset:
|
| 2 |
+
id: SWE-bench/SWE-bench_Verified
|
| 3 |
+
task_id: swe_bench_%_resolved
|
| 4 |
+
value: 62.4
|
| 5 |
+
source:
|
| 6 |
+
url: https://huggingface.co/GAIR/OpenSWE-72B
|
| 7 |
+
name: Model card
|
| 8 |
+
user: nielsr
|
| 9 |
+
notes: SWE-Agent harness
|