# Codebase generation on Online Social Media App (test) Source: [Codebase generation on Online Social Media App (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:45:13.161Z Evaluation of model performance on generating the codebase for an Online Social Media Application, measured by feature completeness, error rates, lines of code (LOC), and test success rates. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Codebase generation | | Dataset (including any stated split) | Online Social Media App (test) | | Metric | Feature Completion (%) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 6 of 6 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Feature Completion (%)](): Higher is better; unit: PERCENT. - [Error Count](): Lower is better; unit: SCALAR. - [LOC](): Higher is better; unit: SIZE. - [Test Success Rate](): Higher is better; unit: PERCENT. ## Recorded results | Method | Feature Completion (%) | Result date | Report paper | | --- | --- | --- | --- | | Code-L2MAC | 82.4 | Not recorded | 68fa79a61e209131cea7ea71 | | AutoGPT | 33.3 | Not recorded | 68fa79a61e209131cea7ea71 | | CodeT | 19.5 | Not recorded | 68fa79a61e209131cea7ea71 | | Reflexion | 19.5 | Not recorded | 68fa79a61e209131cea7ea71 | | Self-Refine | 15.2 | Not recorded | 68fa79a61e209131cea7ea71 | | GPT4 | 13.5 | Not recorded | 68fa79a61e209131cea7ea71 | ### Code-L2MAC Feature Completion (%): 82.4. Result ID: 698b57557a967eddb76dc6ef. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### AutoGPT Feature Completion (%): 33.3. Result ID: 698b57557a967eddb76dc6ee. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"GPT-4"}. This record does not assert independent reproduction. ### CodeT Feature Completion (%): 19.5. Result ID: 698b57557a967eddb76dc6eb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Reflexion Feature Completion (%): 19.5. Result ID: 698b57557a967eddb76dc6ed. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Self-Refine Feature Completion (%): 15.2. Result ID: 698b57557a967eddb76dc6ec. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GPT4 Feature Completion (%): 13.5. Result ID: 698b57557a967eddb76dc6ea. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.