Skip to content

Fix Leaderboard name in Banner #10

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.

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
wants to merge 2 commits into
base: master
Choose a base branch
from

Conversation

SmartManoj
Copy link

@SmartManoj SmartManoj closed this Mar 24, 2025
@SmartManoj
Copy link
Author

It is SOTA on lite and full.

import json
from datasets import load_dataset

result_file = r'evaluation\test\20250227_sweagent-claude-3-7-20250219\results\results.json'

with open(result_file, 'r') as f:
    data = json.load(f)

swebench_lite = load_dataset("princeton-nlp/SWE-bench_Lite", split="test", cache_dir="cache")
swebench_verified = load_dataset("princeton-nlp/SWE-bench_Verified", split="test", cache_dir="cache")
swebench_test = load_dataset("princeton-nlp/SWE-bench", split="test", cache_dir="cache")

filtered_swebench_lite = swebench_lite.filter(lambda x: x['instance_id'] in data['resolved'])
print(f"result_lite: {len(filtered_swebench_lite)}/{len(swebench_lite)} = {(len(filtered_swebench_lite)/len(swebench_lite)):.2%}")

filtered_swebench_verified = swebench_verified.filter(lambda x: x['instance_id'] in data['resolved'])
print(f"result_verified: {len(filtered_swebench_verified)}/{len(swebench_verified)} = {(len(filtered_swebench_verified)/len(swebench_verified)):.2%}")

filtered_swebench_test = swebench_test.filter(lambda x: x['instance_id'] in data['resolved'])
print(f"result_test: {len(filtered_swebench_test)}/{len(swebench_test)} = {(len(filtered_swebench_test)/len(swebench_test)):.2%}")

Output:

result_lite: 141/300 = 47.00%
result_verified: 288/500 = 57.60%
result_test: 776/2294 = 33.83%

@SmartManoj SmartManoj changed the title Fix Leaderboard name Fix Leaderboard name in Banner Mar 24, 2025
@SmartManoj SmartManoj reopened this Mar 24, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant