Add evaluation results on SWE-Bench Verified (#42)
Browse files- Add evaluation results on SWE-Bench Verified (7584eabf4ba1460402b4b7e95103d51acf724d2f)
- Rename .eval_results/swe_bench_verified.yaml A to .eval_results/swe_bench_verified.yaml (f8ed508a03f6c8aadef1d53e02b553aab0446773)
- Update .eval_results/swe_bench_verified.yaml (a2e5c2dbbd5128e04af0d7523d29f799b4b3f19f)
- Update .eval_results/swe_bench_verified.yaml (6543d1bffd005fe14f52d269a39281c524bd63ea)
Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>
.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: 75.80
|
| 5 |
+
source:
|
| 6 |
+
url: https://www.swebench.com/
|
| 7 |
+
name: SWE-Bench official evaluation
|
| 8 |
+
user: nielsr
|
| 9 |
+
notes: high reasoning
|