# Fill-in-the-Middle Code Completion on Real-FIM-Eval Source: [Fill-in-the-Middle Code Completion on Real-FIM-Eval]() Collection index: [llms.txt]() Data updated: 2026-06-04T08:08:33.512Z Evaluation of model performance on Fill-in-the-Middle Code Completion tasks using the Real-FIM-Eval dataset, measured by 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) | Real-FIM-Eval | | 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 | | --- | --- | --- | --- | | SFT | 4.4 | Not recorded | 6a21065bc10484bac23efe7f | | SFT | 4.2 | Not recorded | 6a21065bc10484bac23efe7f | | ORPO | 3.8 | Not recorded | 6a21065bc10484bac23efe7f | | SFT | 3.7 | Not recorded | 6a21065bc10484bac23efe7f | | ORPO | 3.7 | Not recorded | 6a21065bc10484bac23efe7f | | SFT | 3.6 | Not recorded | 6a21065bc10484bac23efe7f | | ORPO | 3.3 | Not recorded | 6a21065bc10484bac23efe7f | | ORPO | 3.3 | Not recorded | 6a21065bc10484bac23efe7f | | DPO | 2.4 | Not recorded | 6a21065bc10484bac23efe7f | | DPO | 2.3 | Not recorded | 6a21065bc10484bac23efe7f | | DPO | 1.7 | Not recorded | 6a21065bc10484bac23efe7f | | DPO | 1.2 | Not recorded | 6a21065bc10484bac23efe7f | | base | 0.4 | Not recorded | 6a21065bc10484bac23efe7f | | base | 0.4 | Not recorded | 6a21065bc10484bac23efe7f | | base | 0.2 | Not recorded | 6a21065bc10484bac23efe7f | | base | 0.2 | Not recorded | 6a21065bc10484bac23efe7f | ### SFT Exact Match (EM): 4.4. Result ID: 6a2131a7fbc373592c1c99b0. [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): 4.2. Result ID: 6a2131a7fbc373592c1c99af. [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): 3.8. Result ID: 6a2131a7fbc373592c1c99b4. [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): 3.7. Result ID: 6a2131a7fbc373592c1c99a8. [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): 3.7. Result ID: 6a2131a7fbc373592c1c99b3. [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): 3.6. Result ID: 6a2131a7fbc373592c1c99a7. [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): 3.3. Result ID: 6a2131a7fbc373592c1c99ab. [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): 3.3. Result ID: 6a2131a7fbc373592c1c99ac. [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): 2.4. Result ID: 6a2131a7fbc373592c1c99b2. [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): 2.3. Result ID: 6a2131a7fbc373592c1c99aa. [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): 1.7. Result ID: 6a2131a7fbc373592c1c99b1. [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): 1.2. Result ID: 6a2131a7fbc373592c1c99a9. [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): 0.4. Result ID: 6a2131a7fbc373592c1c99a6. [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): 0.4. Result ID: 6a2131a7fbc373592c1c99ae. [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): 0.2. Result ID: 6a2131a7fbc373592c1c99a5. [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): 0.2. Result ID: 6a2131a7fbc373592c1c99ad. [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.