# Fill-in-the-Middle Code Completion on SAFIM block Source: [Fill-in-the-Middle Code Completion on SAFIM block]() Collection index: [llms.txt]() Data updated: 2026-06-04T08:08:33.423Z Evaluation of model performance on the Fill-in-the-Middle Code Completion task using the SAFIM block dataset, 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 | | 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 | 30.9 | Not recorded | 6a21065bc10484bac23efe7f | | base | 30.1 | Not recorded | 6a21065bc10484bac23efe7f | | SFT | 26.3 | Not recorded | 6a21065bc10484bac23efe7f | | SFT | 26.3 | Not recorded | 6a21065bc10484bac23efe7f | | ORPO | 25.8 | Not recorded | 6a21065bc10484bac23efe7f | | ORPO | 25.7 | Not recorded | 6a21065bc10484bac23efe7f | | DPO | 24.7 | Not recorded | 6a21065bc10484bac23efe7f | | base | 24.6 | Not recorded | 6a21065bc10484bac23efe7f | | SFT | 24.5 | Not recorded | 6a21065bc10484bac23efe7f | | SFT | 24.5 | Not recorded | 6a21065bc10484bac23efe7f | | ORPO | 23.9 | Not recorded | 6a21065bc10484bac23efe7f | | ORPO | 23.9 | Not recorded | 6a21065bc10484bac23efe7f | | DPO | 19.6 | Not recorded | 6a21065bc10484bac23efe7f | | DPO | 19.3 | Not recorded | 6a21065bc10484bac23efe7f | | DPO | 14.6 | Not recorded | 6a21065bc10484bac23efe7f | | base | 12.4 | Not recorded | 6a21065bc10484bac23efe7f | ### base Exact Match (EM): 30.9. Result ID: 6a2131a7fbc373592c1c9976. [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): 30.1. Result ID: 6a2131a7fbc373592c1c997e. [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): 26.3. Result ID: 6a2131a7fbc373592c1c997f. [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): 26.3. Result ID: 6a2131a7fbc373592c1c9980. [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): 25.8. Result ID: 6a2131a7fbc373592c1c9984. [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): 25.7. Result ID: 6a2131a7fbc373592c1c9983. [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): 24.7. Result ID: 6a2131a7fbc373592c1c9982. [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): 24.6. Result ID: 6a2131a7fbc373592c1c9975. [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): 24.5. Result ID: 6a2131a7fbc373592c1c9977. [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): 24.5. Result ID: 6a2131a7fbc373592c1c9978. [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): 23.9. Result ID: 6a2131a7fbc373592c1c997b. [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): 23.9. Result ID: 6a2131a7fbc373592c1c997c. [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): 19.6. Result ID: 6a2131a7fbc373592c1c9981. [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): 19.3. Result ID: 6a2131a7fbc373592c1c997a. [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): 14.6. Result ID: 6a2131a7fbc373592c1c9979. [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): 12.4. Result ID: 6a2131a7fbc373592c1c997d. [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.