We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
1 parent 405890f commit 84f399cCopy full SHA for 84f399c
1 file changed
analysis/get_results.py
@@ -269,9 +269,6 @@ def get_solve_rate(data_dict, task="complete"):
269
for task_id in range(1140):
270
task_solve_count[f"BigCodeBench/{task_id}"].append(task_perf[f"BigCodeBench/{task_id}"])
271
solve_rate = {task_id: round(np.mean(perfs) * 100, 1) for task_id, perfs in task_solve_count.items()}
272
- with open(f"{task}_solve_rate.txt", "w") as f:
273
- f.write(f"Number of unsolved tasks: {sum([1 for task_id, solve_rate in solve_rate.items() if solve_rate == 0])}\n")
274
- f.write(f"Number of fully solved tasks: {sum([1 for task_id, solve_rate in solve_rate.items() if solve_rate == 100])}\n")
275
return Dataset.from_dict({"task_id": list(solve_rate.keys()), "solve_rate": list(solve_rate.values())})
276
277
0 commit comments