Skip to content

Add agentic arena benchmark #447

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
agmankaruse wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Add agentic arena benchmark #447

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
24 changes: 24 additions & 0 deletions benches/benchmark_tasks.example.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,24 @@
[
{
"id": "json-write-settings",
"category": "file_workflow",
"tools": ["filesystem"],
"goal": "Create settings.json as a JSON object with mode=\"fast\" and retries=2. Use write_file, then FINAL done.",
"oracle": [
{"action": "write_file", "args": {"path": "settings.json", "content": "{\"mode\": \"fast\", \"retries\": 2}"}},
{"final": "done"}
],
"grader": {"type": "file_json_equals", "path": "settings.json", "required": {"mode": "fast", "retries": 2}}
},
{
"id": "json-web-fact",
"category": "web_research",
"tools": ["web_search"],
"goal": "Use web_search to find what the Bradley-Terry model estimates from pairwise outcomes, then FINAL that single word (lowercase).",
"oracle": [
{"action": "web_search", "args": {"query": "bradley terry model pairwise"}},
{"final": "strength"}
],
"grader": {"type": "answer_equals", "expected": "strength", "normalize": "lower_alpha"}
}
]
Loading