LLM Evaluation Report

Model
Date
Total Response Time (s)
Tests Passed
Mean CodeBLEU (0-1)
Mean Usefulness Score (0-4)
Mean Functional Correctness Score (0-4)

o1-preview

2025-02-21

2688.52

126

0.312426

3.57317

3.60976

o1-mini

2025-02-21

999.934

128

0.353161

3.68293

3.7439

gpt-4o

2025-02-21

211.039

124

0.315859

3.67073

3.75

gpt-4o-mini

2025-02-21

228.654

118

0.33717

3.63415

3.68293

claude-3-5-sonnet-20240620

2025-02-21

279.791

110

0.302947

3.68902

3.70732

claude-3-5-sonnet-20241022

2025-02-21

578.256

111

0.325341

3.64634

3.63415

gemini-1.5-pro

2025-02-21

563.298

100

0.329829

3.48171

4.07317

gemini-1.5-flash

2025-02-21

772.702

0

0.264112

0.780488

1.2561

Total Response Time (s): The total time taken by the model to generate all the outputs.

Tests passed: The number of unit tests that the model has passed during evaluation, out of a total of 164 tests.

Mean CodeBLEU: Average CodeBLEU score, a metric for evaluating code generation quality based on both syntactic and semantic correctness.

Mean Usefulness Score: Average rating of the model's output usefulness as rated by a LLM model.

  • 0: Snippet is not at all helpful, it is irrelevant to the problem.

  • 1: Snippet is slightly helpful, it contains information relevant to the problem, but it is easier to write the solution from scratch.

  • 2: Snippet is somewhat helpful, it requires significant changes (compared to the size of the snippet), but is still useful.

  • 3: Snippet is helpful, but needs to be slightly changed to solve the problem.

  • 4: Snippet is very helpful, it solves the problem.

Mean Functional Correctness Score: Average score of the functional correctness of the model's outputs, assessing how well the outputs meet the functional requirements, rated by a LLM model.

  • 0 (failing all possible tests): The code snippet is totally incorrect and meaningless.

  • 4 (passing all possible tests): The code snippet is totally correct and can handle all cases.

Last updated