Hugging Face's logo

Spaces:
taagarwa
/
coding-agent-leaderboard
Running

App Files Community
4
rounakbende commited on
Commit
583c1cf
·
1 Parent(s): 24b60ee

Fix GPT-OSS ansible benchmark name to match leaderboard grouping

Browse files
Files changed (3) hide show
  1. results/swe-bench-pro--ansible-gpt-oss-120b-claude-code.json +1 -1
  2. results/swe-bench-pro--ansible-gpt-oss-120b-opencode.json +1 -1
  3. results/swe-bench-pro--ansible-gpt-oss-120b-pi.json +1 -1
results/swe-bench-pro--ansible-gpt-oss-120b-claude-code.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "benchmark": {
3
- "name": "SWE-Bench Pro",
4
  "repo": "scale-ai/swe-bench-pro",
5
  "num_tasks": 96,
6
  "url": "https://huggingface.co/datasets/scale-ai/swe-bench-pro"
 
1
  {
2
  "benchmark": {
3
+ "name": "SWE-Bench Pro -- Ansible",
4
  "repo": "scale-ai/swe-bench-pro",
5
  "num_tasks": 96,
6
  "url": "https://huggingface.co/datasets/scale-ai/swe-bench-pro"
results/swe-bench-pro--ansible-gpt-oss-120b-opencode.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "benchmark": {
3
- "name": "SWE-Bench Pro",
4
  "repo": "scale-ai/swe-bench-pro",
5
  "num_tasks": 96,
6
  "url": "https://huggingface.co/datasets/scale-ai/swe-bench-pro"
 
1
  {
2
  "benchmark": {
3
+ "name": "SWE-Bench Pro -- Ansible",
4
  "repo": "scale-ai/swe-bench-pro",
5
  "num_tasks": 96,
6
  "url": "https://huggingface.co/datasets/scale-ai/swe-bench-pro"
results/swe-bench-pro--ansible-gpt-oss-120b-pi.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "benchmark": {
3
- "name": "SWE-Bench Pro",
4
  "repo": "scale-ai/swe-bench-pro",
5
  "num_tasks": 96,
6
  "url": "https://huggingface.co/datasets/scale-ai/swe-bench-pro"
 
1
  {
2
  "benchmark": {
3
+ "name": "SWE-Bench Pro -- Ansible",
4
  "repo": "scale-ai/swe-bench-pro",
5
  "num_tasks": 96,
6
  "url": "https://huggingface.co/datasets/scale-ai/swe-bench-pro"