Add community evaluation results for Terminal-Bench 2.1, SWE-Bench Pro
#4
by nielsr HF Staff - opened
.eval_results/swe-bench_pro.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
- dataset:
|
| 2 |
+
id: ScaleAI/SWE-bench_Pro
|
| 3 |
+
task_id: SWE_Bench_Pro
|
| 4 |
+
value: 59.6
|
| 5 |
+
source:
|
| 6 |
+
url: https://huggingface.co/internlm/Atria-Dawn-Preview
|
| 7 |
+
name: Model Card
|
.eval_results/terminal-bench-2.1.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
- dataset:
|
| 2 |
+
id: harborframework/terminal-bench-2.1
|
| 3 |
+
task_id: terminalbench_2_1
|
| 4 |
+
value: 78.3
|
| 5 |
+
source:
|
| 6 |
+
url: https://huggingface.co/internlm/Atria-Dawn-Preview
|
| 7 |
+
name: Model Card
|