We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent f7d3cc8 commit 4cc80a3Copy full SHA for 4cc80a3
bigcodebench/evaluate.py
@@ -131,14 +131,15 @@ def evaluate(flags):
131
else:
132
expected_time = {task_id: None for task_id in problems}
133
134
+ gt_pass_rate = np.mean([1 if v is not None else 0 for v in expected_time.values()])
135
+
136
if os.path.isfile(result_path):
137
print(f"Load from previous results from {result_path}")
138
with open(result_path, "r") as f:
139
results = json.load(f)
140
141
results = compatible_eval_result(results)
142
- gt_pass_rate = np.mean([1 if v is not None else 0 for v in expected_time.values()])
143
144
if flags.check_gt_only:
145
0 commit comments