# Fill-in-the-Middle Code Completion on SAFIM block v2 Source: [Fill-in-the-Middle Code Completion on SAFIM block v2]() Collection index: [llms.txt]() Data updated: 2026-06-04T08:08:33.451Z Evaluation of model performance on the SAFIM block v2 dataset for Fill-in-the-Middle Code Completion tasks, measured using Exact Match (EM) and Edit Similarity (ES). 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 | Fill-in-the-Middle Code Completion | | Dataset (including any stated split) | SAFIM block v2 | | Metric | Exact Match (EM) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 16 of 16 | | 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 - [Exact Match (EM)](): Higher is better; unit: PERCENT. - [Edit Similarity (ES)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Exact Match (EM) | Result date | Report paper | | --- | --- | --- | --- | | base | 37.6 | Not recorded | 6a21065bc10484bac23efe7f | | base | 37.5 | Not recorded | 6a21065bc10484bac23efe7f | | SFT | 32.9 | Not recorded | 6a21065bc10484bac23efe7f | | SFT | 32.9 | Not recorded | 6a21065bc10484bac23efe7f | | ORPO | 32.7 | Not recorded | 6a21065bc10484bac23efe7f | | ORPO | 32.5 | Not recorded | 6a21065bc10484bac23efe7f | | SFT | 31.1 | Not recorded | 6a21065bc10484bac23efe7f | | SFT | 31.1 | Not recorded | 6a21065bc10484bac23efe7f | | ORPO | 31.1 | Not recorded | 6a21065bc10484bac23efe7f | | ORPO | 31.1 | Not recorded | 6a21065bc10484bac23efe7f | | DPO | 30.2 | Not recorded | 6a21065bc10484bac23efe7f | | base | 27.3 | Not recorded | 6a21065bc10484bac23efe7f | | DPO | 24.5 | Not recorded | 6a21065bc10484bac23efe7f | | DPO | 22.2 | Not recorded | 6a21065bc10484bac23efe7f | | DPO | 15.3 | Not recorded | 6a21065bc10484bac23efe7f | | base | 13.4 | Not recorded | 6a21065bc10484bac23efe7f | ### base Exact Match (EM): 37.6. Result ID: 6a2131a7fbc373592c1c998e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"7B","Truncation Strategy":"+trunc"}. This record does not assert independent reproduction. ### base Exact Match (EM): 37.5. Result ID: 6a2131a7fbc373592c1c9986. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"3B","Truncation Strategy":"+trunc"}. This record does not assert independent reproduction. ### SFT Exact Match (EM): 32.9. Result ID: 6a2131a7fbc373592c1c998f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"7B","Truncation Strategy":"untruncated"}. This record does not assert independent reproduction. ### SFT Exact Match (EM): 32.9. Result ID: 6a2131a7fbc373592c1c9990. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"7B","Truncation Strategy":"+trunc"}. This record does not assert independent reproduction. ### ORPO Exact Match (EM): 32.7. Result ID: 6a2131a7fbc373592c1c9994. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"7B","Truncation Strategy":"+trunc"}. This record does not assert independent reproduction. ### ORPO Exact Match (EM): 32.5. Result ID: 6a2131a7fbc373592c1c9993. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"7B","Truncation Strategy":"untruncated"}. This record does not assert independent reproduction. ### SFT Exact Match (EM): 31.1. Result ID: 6a2131a7fbc373592c1c9987. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"3B","Truncation Strategy":"untruncated"}. This record does not assert independent reproduction. ### SFT Exact Match (EM): 31.1. Result ID: 6a2131a7fbc373592c1c9988. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"3B","Truncation Strategy":"+trunc"}. This record does not assert independent reproduction. ### ORPO Exact Match (EM): 31.1. Result ID: 6a2131a7fbc373592c1c998b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"3B","Truncation Strategy":"untruncated"}. This record does not assert independent reproduction. ### ORPO Exact Match (EM): 31.1. Result ID: 6a2131a7fbc373592c1c998c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"3B","Truncation Strategy":"+trunc"}. This record does not assert independent reproduction. ### DPO Exact Match (EM): 30.2. Result ID: 6a2131a7fbc373592c1c9992. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"7B","Truncation Strategy":"+trunc"}. This record does not assert independent reproduction. ### base Exact Match (EM): 27.3. Result ID: 6a2131a7fbc373592c1c9985. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"3B","Truncation Strategy":"untruncated"}. This record does not assert independent reproduction. ### DPO Exact Match (EM): 24.5. Result ID: 6a2131a7fbc373592c1c998a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"3B","Truncation Strategy":"+trunc"}. This record does not assert independent reproduction. ### DPO Exact Match (EM): 22.2. Result ID: 6a2131a7fbc373592c1c9991. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"7B","Truncation Strategy":"untruncated"}. This record does not assert independent reproduction. ### DPO Exact Match (EM): 15.3. Result ID: 6a2131a7fbc373592c1c9989. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"3B","Truncation Strategy":"untruncated"}. This record does not assert independent reproduction. ### base Exact Match (EM): 13.4. Result ID: 6a2131a7fbc373592c1c998d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"7B","Truncation Strategy":"untruncated"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.