# Knowledge Editing on MQuAKE (Edit Success Rate and Neighborhood Score) Source: [Knowledge Editing on MQuAKE (Edit Success Rate and Neighborhood Score)]() Collection index: [llms.txt]() Data updated: 2026-05-19T08:49:57.250Z Evaluation of Knowledge Editing performance on the MQuAKE dataset, measured by Edit Success Rate ('Edit succ.') and Neighborhood Score ('Nei.'). 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 | Knowledge Editing | | Dataset (including any stated split) | MQuAKE | | Metric | Edit Success Rate | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 48 of 48 | | 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 - [Edit Success Rate](): Higher is better; unit: PERCENT. - [Neighborhood Score](): Higher is better; unit: PERCENT. - [Train Success Rate](): Higher is better; unit: PERCENT. - [Retrieval Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Edit Success Rate | Result date | Report paper | | --- | --- | --- | --- | | CoT2Edit | 99.95 | Not recorded | 69d5e0f97d0172140ec7599f | | CoT2Edit | 99.48 | Not recorded | 69d5e0f97d0172140ec7599f | | CoT2Edit | 99.22 | Not recorded | 69d5e0f97d0172140ec7599f | | AlphaEdit | 97.73 | Not recorded | 69d5e0f97d0172140ec7599f | | LTE | 97.73 | Not recorded | 69d5e0f97d0172140ec7599f | | AlphaEdit | 97.71 | Not recorded | 69d5e0f97d0172140ec7599f | | AlphaEdit | 97.11 | Not recorded | 69d5e0f97d0172140ec7599f | | EditCoT | 96.73 | Not recorded | 69d5e0f97d0172140ec7599f | | GLAME | 96.68 | Not recorded | 69d5e0f97d0172140ec7599f | | PMET | 96.37 | Not recorded | 69d5e0f97d0172140ec7599f | | EditCoT | 96.37 | Not recorded | 69d5e0f97d0172140ec7599f | | GLAME | 95.56 | Not recorded | 69d5e0f97d0172140ec7599f | | LTE | 94.51 | Not recorded | 69d5e0f97d0172140ec7599f | | PMET | 94.13 | Not recorded | 69d5e0f97d0172140ec7599f | | LTE | 93.46 | Not recorded | 69d5e0f97d0172140ec7599f | | GLAME | 93.28 | Not recorded | 69d5e0f97d0172140ec7599f | | PMET | 93.16 | Not recorded | 69d5e0f97d0172140ec7599f | | MEMIT | 91.65 | Not recorded | 69d5e0f97d0172140ec7599f | | SKEME | 90.98 | Not recorded | 69d5e0f97d0172140ec7599f | | EditCoT | 90.58 | Not recorded | 69d5e0f97d0172140ec7599f | | SKEME | 88.05 | Not recorded | 69d5e0f97d0172140ec7599f | | MEMIT | 87.68 | Not recorded | 69d5e0f97d0172140ec7599f | | IKE | 87.44 | Not recorded | 69d5e0f97d0172140ec7599f | | SKEME | 87.28 | Not recorded | 69d5e0f97d0172140ec7599f | | IKE | 86.63 | Not recorded | 69d5e0f97d0172140ec7599f | | IKE | 84.93 | Not recorded | 69d5e0f97d0172140ec7599f | | MEMIT | 81.19 | Not recorded | 69d5e0f97d0172140ec7599f | | RoME | 80.74 | Not recorded | 69d5e0f97d0172140ec7599f | | RoME | 80.28 | Not recorded | 69d5e0f97d0172140ec7599f | | RoME | 80.13 | Not recorded | 69d5e0f97d0172140ec7599f | ### CoT2Edit Edit Success Rate: 99.95. Result ID: 69d612c247f34ce924bea338. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LLaMA3-8B"}. This record does not assert independent reproduction. ### CoT2Edit Edit Success Rate: 99.48. Result ID: 69d612c247f34ce924bea342. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Falcon3-10B"}. This record does not assert independent reproduction. ### CoT2Edit Edit Success Rate: 99.22. Result ID: 69d612c247f34ce924bea34c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-14B"}. This record does not assert independent reproduction. ### AlphaEdit Edit Success Rate: 97.73. Result ID: 69d612c247f34ce924bea341. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Falcon3-10B"}. This record does not assert independent reproduction. ### LTE Edit Success Rate: 97.73. Result ID: 69d612c247f34ce924bea348. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Qwen3-14B"}. This record does not assert independent reproduction. ### AlphaEdit Edit Success Rate: 97.71. Result ID: 69d612c247f34ce924bea34b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-14B"}. This record does not assert independent reproduction. ### AlphaEdit Edit Success Rate: 97.11. Result ID: 69d612c247f34ce924bea337. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LLaMA3-8B"}. This record does not assert independent reproduction. ### EditCoT Edit Success Rate: 96.73. Result ID: 69d612c247f34ce924bea33d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Falcon3-10B"}. This record does not assert independent reproduction. ### GLAME Edit Success Rate: 96.68. Result ID: 69d612c247f34ce924bea340. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Falcon3-10B"}. This record does not assert independent reproduction. ### PMET Edit Success Rate: 96.37. Result ID: 69d612c247f34ce924bea335. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LLaMA3-8B"}. This record does not assert independent reproduction. ### EditCoT Edit Success Rate: 96.37. Result ID: 69d612c247f34ce924bea347. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-14B"}. This record does not assert independent reproduction. ### GLAME Edit Success Rate: 95.56. Result ID: 69d612c247f34ce924bea34a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-14B"}. This record does not assert independent reproduction. ### LTE Edit Success Rate: 94.51. Result ID: 69d612c247f34ce924bea33e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Falcon3-10B"}. This record does not assert independent reproduction. ### PMET Edit Success Rate: 94.13. Result ID: 69d612c247f34ce924bea349. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-14B"}. This record does not assert independent reproduction. ### LTE Edit Success Rate: 93.46. Result ID: 69d612c247f34ce924bea334. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"LLaMA3-8B"}. This record does not assert independent reproduction. ### GLAME Edit Success Rate: 93.28. Result ID: 69d612c247f34ce924bea336. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LLaMA3-8B"}. This record does not assert independent reproduction. ### PMET Edit Success Rate: 93.16. Result ID: 69d612c247f34ce924bea33f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Falcon3-10B"}. This record does not assert independent reproduction. ### MEMIT Edit Success Rate: 91.65. Result ID: 69d612c247f34ce924bea344. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-14B"}. This record does not assert independent reproduction. ### SKEME Edit Success Rate: 90.98. Result ID: 69d612c247f34ce924bea33c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Falcon3-10B"}. This record does not assert independent reproduction. ### EditCoT Edit Success Rate: 90.58. Result ID: 69d612c247f34ce924bea333. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LLaMA3-8B"}. This record does not assert independent reproduction. ### SKEME Edit Success Rate: 88.05. Result ID: 69d612c247f34ce924bea332. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LLaMA3-8B"}. This record does not assert independent reproduction. ### MEMIT Edit Success Rate: 87.68. Result ID: 69d612c247f34ce924bea33a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Falcon3-10B"}. This record does not assert independent reproduction. ### IKE Edit Success Rate: 87.44. Result ID: 69d612c247f34ce924bea33b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Falcon3-10B"}. This record does not assert independent reproduction. ### SKEME Edit Success Rate: 87.28. Result ID: 69d612c247f34ce924bea346. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-14B"}. This record does not assert independent reproduction. ### IKE Edit Success Rate: 86.63. Result ID: 69d612c247f34ce924bea331. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LLaMA3-8B"}. This record does not assert independent reproduction. ### IKE Edit Success Rate: 84.93. Result ID: 69d612c247f34ce924bea345. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-14B"}. This record does not assert independent reproduction. ### MEMIT Edit Success Rate: 81.19. Result ID: 69d612c247f34ce924bea330. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LLaMA3-8B"}. This record does not assert independent reproduction. ### RoME Edit Success Rate: 80.74. Result ID: 69d612c247f34ce924bea343. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Qwen3-14B"}. This record does not assert independent reproduction. ### RoME Edit Success Rate: 80.28. Result ID: 69d612c247f34ce924bea32f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"LLaMA3-8B"}. This record does not assert independent reproduction. ### RoME Edit Success Rate: 80.13. Result ID: 69d612c247f34ce924bea339. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Falcon3-10B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.