# Knowledge-grounded Dialogue on Wizard of Wikipedia (WoW) Source: [Knowledge-grounded Dialogue on Wizard of Wikipedia (WoW)]() Collection index: [llms.txt]() Data updated: 2026-04-10T08:56:21.750Z Evaluation of Knowledge-grounded Dialogue performance on the Wizard of Wikipedia (WoW) dataset, measured using a general performance score. 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-grounded Dialogue | | Dataset (including any stated split) | Wizard of Wikipedia (WoW) | | Metric | Performance Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 32 of 32 | | 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 - [Performance Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Performance Score | Result date | Report paper | | --- | --- | --- | --- | | o1 | 78.6 | Not recorded | 69d8842a7d0172140ec77ac3 | | GuarantRAG | 77.8 | Not recorded | 69d8842a7d0172140ec77ac3 | | GPT-4o | 77.2 | Not recorded | 69d8842a7d0172140ec77ac3 | | GuarantRAG | 76.2 | Not recorded | 69d8842a7d0172140ec77ac3 | | GuarantRAG | 75.1 | Not recorded | 69d8842a7d0172140ec77ac3 | | P-RAG | 74.3 | Not recorded | 69d8842a7d0172140ec77ac3 | | P-RAG | 73.8 | Not recorded | 69d8842a7d0172140ec77ac3 | | SOLAR | 72.4 | Not recorded | 69d8842a7d0172140ec77ac3 | | SOLAR | 72.1 | Not recorded | 69d8842a7d0172140ec77ac3 | | DRAGIN | 72 | Not recorded | 69d8842a7d0172140ec77ac3 | | DRAGIN | 71.6 | Not recorded | 69d8842a7d0172140ec77ac3 | | FLARE | 71.5 | Not recorded | 69d8842a7d0172140ec77ac3 | | P-RAG | 71.2 | Not recorded | 69d8842a7d0172140ec77ac3 | | FLARE | 71.2 | Not recorded | 69d8842a7d0172140ec77ac3 | | RQ-RAG | 70.9 | Not recorded | 69d8842a7d0172140ec77ac3 | | RQ-RAG | 70.4 | Not recorded | 69d8842a7d0172140ec77ac3 | | SOLAR | 69.5 | Not recorded | 69d8842a7d0172140ec77ac3 | | SelfRAG | 69.3 | Not recorded | 69d8842a7d0172140ec77ac3 | | DRAGIN | 69.1 | Not recorded | 69d8842a7d0172140ec77ac3 | | SelfRAG | 68.9 | Not recorded | 69d8842a7d0172140ec77ac3 | | FLARE | 68.7 | Not recorded | 69d8842a7d0172140ec77ac3 | | DA-RAG | 68.2 | Not recorded | 69d8842a7d0172140ec77ac3 | | RQ-RAG | 68.1 | Not recorded | 69d8842a7d0172140ec77ac3 | | DA-RAG | 67.8 | Not recorded | 69d8842a7d0172140ec77ac3 | | SelfRAG | 66.8 | Not recorded | 69d8842a7d0172140ec77ac3 | | DA-RAG | 65.4 | Not recorded | 69d8842a7d0172140ec77ac3 | | Standard RAG | 65.1 | Not recorded | 69d8842a7d0172140ec77ac3 | | Standard RAG | 64.7 | Not recorded | 69d8842a7d0172140ec77ac3 | | Standard RAG | 62.7 | Not recorded | 69d8842a7d0172140ec77ac3 | | Qwen3-14B-T | 59.3 | Not recorded | 69d8842a7d0172140ec77ac3 | | Qwen3-14B | 58.7 | Not recorded | 69d8842a7d0172140ec77ac3 | | Qwen3-8B | 56.2 | Not recorded | 69d8842a7d0172140ec77ac3 | ### o1 Performance Score: 78.6. Result ID: 69d8bb2d47f34ce924c1bd6d. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GuarantRAG Performance Score: 77.8. Result ID: 69d8bb2d47f34ce924c1bd61. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen3-14B","Thinking Mode":"false"}. This record does not assert independent reproduction. ### GPT-4o Performance Score: 77.2. Result ID: 69d8bb2d47f34ce924c1bd6c. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GuarantRAG Performance Score: 76.2. Result ID: 69d8bb2d47f34ce924c1bd6b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen3-14B","Thinking Mode":"true"}. This record does not assert independent reproduction. ### GuarantRAG Performance Score: 75.1. Result ID: 69d8bb2d47f34ce924c1bd57. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen3-8B","Thinking Mode":"false"}. This record does not assert independent reproduction. ### P-RAG Performance Score: 74.3. Result ID: 69d8bb2d47f34ce924c1bd60. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen3-14B","Thinking Mode":"false"}. This record does not assert independent reproduction. ### P-RAG Performance Score: 73.8. Result ID: 69d8bb2d47f34ce924c1bd6a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen3-14B","Thinking Mode":"true"}. This record does not assert independent reproduction. ### SOLAR Performance Score: 72.4. Result ID: 69d8bb2d47f34ce924c1bd5c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen3-14B","Thinking Mode":"false"}. This record does not assert independent reproduction. ### SOLAR Performance Score: 72.1. Result ID: 69d8bb2d47f34ce924c1bd66. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen3-14B","Thinking Mode":"true"}. This record does not assert independent reproduction. ### DRAGIN Performance Score: 72. Result ID: 69d8bb2d47f34ce924c1bd5f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen3-14B","Thinking Mode":"false"}. This record does not assert independent reproduction. ### DRAGIN Performance Score: 71.6. Result ID: 69d8bb2d47f34ce924c1bd69. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen3-14B","Thinking Mode":"true"}. This record does not assert independent reproduction. ### FLARE Performance Score: 71.5. Result ID: 69d8bb2d47f34ce924c1bd5e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen3-14B","Thinking Mode":"false"}. This record does not assert independent reproduction. ### P-RAG Performance Score: 71.2. Result ID: 69d8bb2d47f34ce924c1bd56. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen3-8B","Thinking Mode":"false"}. This record does not assert independent reproduction. ### FLARE Performance Score: 71.2. Result ID: 69d8bb2d47f34ce924c1bd68. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen3-14B","Thinking Mode":"true"}. This record does not assert independent reproduction. ### RQ-RAG Performance Score: 70.9. Result ID: 69d8bb2d47f34ce924c1bd5b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen3-14B","Thinking Mode":"false"}. This record does not assert independent reproduction. ### RQ-RAG Performance Score: 70.4. Result ID: 69d8bb2d47f34ce924c1bd65. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen3-14B","Thinking Mode":"true"}. This record does not assert independent reproduction. ### SOLAR Performance Score: 69.5. Result ID: 69d8bb2d47f34ce924c1bd52. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen3-8B","Thinking Mode":"false"}. This record does not assert independent reproduction. ### SelfRAG Performance Score: 69.3. Result ID: 69d8bb2d47f34ce924c1bd5a. [Reporting paper]() Recorded evaluation configuration: {"Base Model":"Qwen3-14B","Thinking Mode":"false"}. This record does not assert independent reproduction. ### DRAGIN Performance Score: 69.1. Result ID: 69d8bb2d47f34ce924c1bd55. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen3-8B","Thinking Mode":"false"}. This record does not assert independent reproduction. ### SelfRAG Performance Score: 68.9. Result ID: 69d8bb2d47f34ce924c1bd64. [Reporting paper]() Recorded evaluation configuration: {"Base Model":"Qwen3-14B","Thinking Mode":"true"}. This record does not assert independent reproduction. ### FLARE Performance Score: 68.7. Result ID: 69d8bb2d47f34ce924c1bd54. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen3-8B","Thinking Mode":"false"}. This record does not assert independent reproduction. ### DA-RAG Performance Score: 68.2. Result ID: 69d8bb2d47f34ce924c1bd5d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen3-14B","Thinking Mode":"false"}. This record does not assert independent reproduction. ### RQ-RAG Performance Score: 68.1. Result ID: 69d8bb2d47f34ce924c1bd51. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen3-8B","Thinking Mode":"false"}. This record does not assert independent reproduction. ### DA-RAG Performance Score: 67.8. Result ID: 69d8bb2d47f34ce924c1bd67. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen3-14B","Thinking Mode":"true"}. This record does not assert independent reproduction. ### SelfRAG Performance Score: 66.8. Result ID: 69d8bb2d47f34ce924c1bd50. [Reporting paper]() Recorded evaluation configuration: {"Base Model":"Qwen3-8B","Thinking Mode":"false"}. This record does not assert independent reproduction. ### DA-RAG Performance Score: 65.4. Result ID: 69d8bb2d47f34ce924c1bd53. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen3-8B","Thinking Mode":"false"}. This record does not assert independent reproduction. ### Standard RAG Performance Score: 65.1. Result ID: 69d8bb2d47f34ce924c1bd59. [Reporting paper]() Recorded evaluation configuration: {"Base Model":"Qwen3-14B","Thinking Mode":"false"}. This record does not assert independent reproduction. ### Standard RAG Performance Score: 64.7. Result ID: 69d8bb2d47f34ce924c1bd63. [Reporting paper]() Recorded evaluation configuration: {"Base Model":"Qwen3-14B","Thinking Mode":"true"}. This record does not assert independent reproduction. ### Standard RAG Performance Score: 62.7. Result ID: 69d8bb2d47f34ce924c1bd4f. [Reporting paper]() Recorded evaluation configuration: {"Base Model":"Qwen3-8B","Thinking Mode":"false"}. This record does not assert independent reproduction. ### Qwen3-14B-T Performance Score: 59.3. Result ID: 69d8bb2d47f34ce924c1bd62. [Reporting paper]() Recorded evaluation configuration: {"Base Model":"Qwen3-14B","Thinking Mode":"true"}. This record does not assert independent reproduction. ### Qwen3-14B Performance Score: 58.7. Result ID: 69d8bb2d47f34ce924c1bd58. [Reporting paper]() Recorded evaluation configuration: {"Base Model":"Qwen3-14B","Thinking Mode":"false"}. This record does not assert independent reproduction. ### Qwen3-8B Performance Score: 56.2. Result ID: 69d8bb2d47f34ce924c1bd4e. [Reporting paper]() Recorded evaluation configuration: {"Base Model":"Qwen3-8B","Thinking Mode":"false"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.