Remove SWE-Bench Pro eval result (moved to PCL-RSI-lab/Seshat-agent)
Browse files
.eval_results/swe_bench_pro.yaml
DELETED
|
@@ -1,10 +0,0 @@
|
|
| 1 |
-
- dataset:
|
| 2 |
-
id: ScaleAI/SWE-bench_Pro
|
| 3 |
-
task_id: SWE_Bench_Pro
|
| 4 |
-
value: 94.94
|
| 5 |
-
date: "2026-10-27"
|
| 6 |
-
source:
|
| 7 |
-
url: https://huggingface.co/datasets/PCL-RSI-lab/SWE-Bench-Pro-Evaluation-Evidence
|
| 8 |
-
name: SWE-Bench Pro v1 evaluation evidence (731 instances)
|
| 9 |
-
user: PCL-RSI-lab
|
| 10 |
-
notes: "Seshat/MetaEvo + Kimi K3; SWE-Bench Pro v1 (731), resolve rate 694/731=94.94%; community self-report pending V2 regrade"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|