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 | 2024-11-21 | 2208.03 | 132 | 0.321908 | 3.60976 | 3.64024 |
o1-mini | 2024-11-21 | 718.012 | 134 | 0.322883 | 3.65244 | 3.7561 |
gpt-4o | 2024-11-21 | 321.525 | 125 | 0.316051 | 3.70732 | 3.7439 |
gpt-4o-mini | 2024-11-21 | 191.192 | 114 | 0.339313 | 3.62805 | 3.69512 |
claude-3-5-sonnet-20240620 | 2024-11-21 | 335.662 | 113 | 0.303122 | 3.60366 | 3.62195 |
claude-3-5-sonnet-20241022 | 2024-11-21 | 351.938 | 110 | 0.321726 | 3.67073 | 3.67683 |
gemini-1.5-pro | 2024-11-21 | 528.459 | 106 | 0.340196 | 3.43293 | 3.5061 |
gemini-1.5-flash | 2024-11-21 | 759.693 | 2 | 0.270065 | 0.670732 | 0.829268 |
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