results = await limited_get_score(eval_ds) # Scoring: 80%|████████ | 40/50 [00:22<00:04, 2.36sample/s] # calculate the average score total_score = sum([r["total_score"] for r in results]) / len(results) print(f"Average Score: {total_score}") # extract and sample with score 0 score_0 = [r for r in results if r["total_score"] == 0] print(f"Samples with score 0: {len(score_0)}")