Add SWE-bench Pro evaluation result (50.7%)
#101
by SaylorTwift HF Staff - opened
.eval_results/swe_bench_pro.yaml
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
- dataset:
|
| 2 |
+
id: ScaleAI/SWE-bench_Pro
|
| 3 |
+
task_id: SWE_Bench_Pro
|
| 4 |
+
value: 50.7
|
| 5 |
+
date: '2026-03-17'
|
| 6 |
+
source:
|
| 7 |
+
url: https://huggingface.co/moonshotai/Kimi-K2.5
|
| 8 |
+
name: Model Card
|
| 9 |
+
user: SaylorTwift
|