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

2024-12-21

2222.02

135

0.315387

3.60366

3.62195

o1-mini

2024-12-21

742.336

128

0.34076

3.70122

3.71341

gpt-4o

2024-12-21

328.26

124

0.321923

3.70732

3.68293

gpt-4o-mini

2024-12-21

209.742

122

0.335439

3.64024

3.63415

claude-3-5-sonnet-20240620

2024-12-21

295.78

117

0.299314

3.66463

3.63415

claude-3-5-sonnet-20241022

2024-12-21

263.51

114

0.330973

3.67073

3.62805

gemini-1.5-pro

2024-12-21

507.269

94

0.347441

3.45122

3.43293

gemini-1.5-flash

2024-12-21

768.506

1

0.263737

0.628049

0.835366

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