yanjzh commited on
Commit
20e1db8
·
verified ·
1 Parent(s): 8709ac5

Remove SWE-Bench Pro eval result (moved to PCL-RSI-lab/Seshat-agent)

Browse files
Files changed (1) hide show
  1. .eval_results/swe_bench_pro.yaml +0 -10
.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"