# Fill-in-the-Middle Code Completion on SAFIM control Source: [Fill-in-the-Middle Code Completion on SAFIM control]() Collection index: [llms.txt]() Data updated: 2026-06-04T08:08:33.482Z Evaluation of model performance on the SAFIM control 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 control | | 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 | | --- | --- | --- | --- | | ORPO | 41 | Not recorded | 6a21065bc10484bac23efe7f | | ORPO | 41 | Not recorded | 6a21065bc10484bac23efe7f | | SFT | 39.3 | Not recorded | 6a21065bc10484bac23efe7f | | SFT | 39.2 | Not recorded | 6a21065bc10484bac23efe7f | | SFT | 36.4 | Not recorded | 6a21065bc10484bac23efe7f | | SFT | 36.4 | Not recorded | 6a21065bc10484bac23efe7f | | base | 35.3 | Not recorded | 6a21065bc10484bac23efe7f | | base | 34.7 | Not recorded | 6a21065bc10484bac23efe7f | | ORPO | 34.3 | Not recorded | 6a21065bc10484bac23efe7f | | ORPO | 34.3 | Not recorded | 6a21065bc10484bac23efe7f | | DPO | 15 | Not recorded | 6a21065bc10484bac23efe7f | | DPO | 14 | Not recorded | 6a21065bc10484bac23efe7f | | DPO | 12 | Not recorded | 6a21065bc10484bac23efe7f | | DPO | 8.9 | Not recorded | 6a21065bc10484bac23efe7f | | base | 7.6 | Not recorded | 6a21065bc10484bac23efe7f | | base | 4.8 | Not recorded | 6a21065bc10484bac23efe7f | ### ORPO Exact Match (EM): 41. Result ID: 6a2131a7fbc373592c1c99a3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"7B","Truncation Strategy":"untruncated"}. This record does not assert independent reproduction. ### ORPO Exact Match (EM): 41. Result ID: 6a2131a7fbc373592c1c99a4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"7B","Truncation Strategy":"+trunc"}. This record does not assert independent reproduction. ### SFT Exact Match (EM): 39.3. Result ID: 6a2131a7fbc373592c1c99a0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"7B","Truncation Strategy":"+trunc"}. This record does not assert independent reproduction. ### SFT Exact Match (EM): 39.2. Result ID: 6a2131a7fbc373592c1c999f. [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): 36.4. Result ID: 6a2131a7fbc373592c1c9997. [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): 36.4. Result ID: 6a2131a7fbc373592c1c9998. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"3B","Truncation Strategy":"+trunc"}. This record does not assert independent reproduction. ### base Exact Match (EM): 35.3. Result ID: 6a2131a7fbc373592c1c9996. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"3B","Truncation Strategy":"+trunc"}. This record does not assert independent reproduction. ### base Exact Match (EM): 34.7. Result ID: 6a2131a7fbc373592c1c9995. [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): 34.3. Result ID: 6a2131a7fbc373592c1c999b. [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): 34.3. Result ID: 6a2131a7fbc373592c1c999c. [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): 15. Result ID: 6a2131a7fbc373592c1c999a. [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): 14. Result ID: 6a2131a7fbc373592c1c9999. [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): 12. Result ID: 6a2131a7fbc373592c1c99a2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"7B","Truncation Strategy":"+trunc"}. This record does not assert independent reproduction. ### DPO Exact Match (EM): 8.9. Result ID: 6a2131a7fbc373592c1c99a1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"7B","Truncation Strategy":"untruncated"}. This record does not assert independent reproduction. ### base Exact Match (EM): 7.6. Result ID: 6a2131a7fbc373592c1c999e. [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): 4.8. Result ID: 6a2131a7fbc373592c1c999d. [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.