LLM Zoomcamp 2025

Homework 2: Vector Search Statistics

Distribution of scores and reported study time for this homework.

Submissions

328

Median total score

Average total score

Score distribution

All values are points.

Metric	Min	Q1	Median	Average	Q3	Max
Questions score	-	7.0	7.0	6.5	7.0	7
Learning in public score	-	0.0	0.0	0.5	0.0	7
Total score	-	7.0	7.0	7.1	7.0	15

Questions score

Min: -
Median: 7.0
Max: 7
Q1: 7.0
Avg: 6.5
Q3: 7.0

Learning in public score

Min: -
Median: 0.0
Max: 7
Q1: 0.0
Avg: 0.5
Q3: 0.0

Total score

Min: -
Median: 7.0
Max: 15
Q1: 7.0
Avg: 7.1
Q3: 7.0

Time distribution

All values are hours reported by students.

Metric	Min	Q1	Median	Average	Q3	Max
Lectures	1.0	2.0	3.0	5.1	5.8	48.0
Homework	0.0	1.4	2.0	3.4	4.0	72.0

Lectures

Min: 1.0
Median: 3.0
Max: 48.0
Q1: 2.0
Avg: 5.1
Q3: 5.8

Homework

Min: 0.0
Median: 2.0
Max: 72.0
Q1: 1.4
Avg: 3.4
Q3: 4.0

Question breakdown

Correctness and answer distribution per question.

1. Embedding the query

313 / 327 correct (95.7%)

1 -0.51 9 (2.8%)

2 -0.11 313 (95.7%)

3 0 0 (0.0%)

4 0.51 3 (0.9%)

2. Cosine similarity with another vector

311 / 327 correct (95.1%)

1 0.3 1 (0.3%)

2 0.5 2 (0.6%)

3 0.7 12 (3.7%)

4 0.9 311 (95.1%)

3. Ranking by cosine

293 / 327 correct (89.6%)

1 0 17 (5.2%)

2 1 293 (89.6%)

3 2 6 (1.8%)

4 3 8 (2.4%)

5 4 2 (0.6%)

4. Ranking by cosine, version two

304 / 327 correct (93.0%)

1 0 304 (93.0%)

2 1 8 (2.4%)

3 2 6 (1.8%)

4 3 4 (1.2%)

5 4 3 (0.9%)

5. Selecting the embedding model

312 / 327 correct (95.4%)

1 128 8 (2.4%)

2 256 4 (1.2%)

3 384 312 (95.4%)

4 512 1 (0.3%)

6. Indexing with qdrant

299 / 327 correct (91.4%)

1 0.97 11 (3.4%)

2 0.87 299 (91.4%)

3 0.77 13 (4.0%)

4 0.67 3 (0.9%)

Calculated: 16 July 2025, 09:27