Add community evaluation results for SWE-BENCH_VERIFIED
#10
by nielsr HF Staff - opened
.eval_results/swe-bench_verified.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
- dataset:
|
| 2 |
+
id: SWE-bench/SWE-bench_Verified
|
| 3 |
+
task_id: swe_bench_%_resolved
|
| 4 |
+
value: 77.6
|
| 5 |
+
source:
|
| 6 |
+
url: https://huggingface.co/mistralai/Mistral-Medium-3.5-128B
|
| 7 |
+
name: Model Card
|