# Knowledge Base Question Answering on QALD en Freebase 10 (test) Source: [Knowledge Base Question Answering on QALD en Freebase 10 (test)]() Collection index: [llms.txt]() Data updated: 2026-03-24T15:24:17.750Z Evaluation of model performance on the test split of the QALD 10 dataset, utilizing the Freebase knowledge source, for Knowledge Base Question Answering. 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 Base Question Answering | | Dataset (including any stated split) | QALD en Freebase 10 (test) | | Metric | Hits@1 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 14 of 14 | | 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 - [Hits@1](): Higher is better; unit: PERCENT. ## Recorded results | Method | Hits@1 | Result date | Report paper | | --- | --- | --- | --- | | KG-Hopper w/Qwen-2.5-7B | 74.28 | Not recorded | 69c21a9c0636e5bf4afc496d | | GPT-4o-mini + KG | 72.86 | Not recorded | 69c21a9c0636e5bf4afc496d | | LLaMA-3.3-70B + KG | 71.78 | Not recorded | 69c21a9c0636e5bf4afc496d | | DeepSeek-R1-Distill-Llama-70B + KG | 66.1 | Not recorded | 69c21a9c0636e5bf4afc496d | | Qwen-2.5-7B (SFT) + KG | 65.18 | Not recorded | 69c21a9c0636e5bf4afc496d | | LLaMA-3.1-8B (SFT) + KG | 59.63 | Not recorded | 69c21a9c0636e5bf4afc496d | | Qwen-2.5-7B + KG | 56.54 | Not recorded | 69c21a9c0636e5bf4afc496d | | GPT-4o | 56.2 | Not recorded | 69c21a9c0636e5bf4afc496d | | LLaMA-3.3-70B | 56 | Not recorded | 69c21a9c0636e5bf4afc496d | | LLaMA-3.1-8B + KG | 55.73 | Not recorded | 69c21a9c0636e5bf4afc496d | | GPT-4o-mini | 51.98 | Not recorded | 69c21a9c0636e5bf4afc496d | | DeepSeek-R1-Distill-Llama-70B | 43.1 | Not recorded | 69c21a9c0636e5bf4afc496d | | Qwen-2.5-7B | 41.88 | Not recorded | 69c21a9c0636e5bf4afc496d | | LLaMA-3.1-8B | 40.25 | Not recorded | 69c21a9c0636e5bf4afc496d | ### KG-Hopper w/Qwen-2.5-7B Hits@1: 74.28. Result ID: 69c2ac9047f34ce924abb497. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B","Strategy":"KG-Augmented with RL Fine-Tuning"}. This record does not assert independent reproduction. ### GPT-4o-mini + KG Hits@1: 72.86. Result ID: 69c2ac9047f34ce924abb494. [Reporting paper]() Recorded evaluation configuration: {"Strategy":"KG-Augmented without Fine-Tuning"}. This record does not assert independent reproduction. ### LLaMA-3.3-70B + KG Hits@1: 71.78. Result ID: 69c2ac9047f34ce924abb492. [Reporting paper]() Recorded evaluation configuration: {"Size":"70B","Strategy":"KG-Augmented without Fine-Tuning"}. This record does not assert independent reproduction. ### DeepSeek-R1-Distill-Llama-70B + KG Hits@1: 66.1. Result ID: 69c2ac9047f34ce924abb493. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"70B","Strategy":"KG-Augmented without Fine-Tuning"}. This record does not assert independent reproduction. ### Qwen-2.5-7B (SFT) + KG Hits@1: 65.18. Result ID: 69c2ac9047f34ce924abb495. [Reporting paper]() Recorded evaluation configuration: {"Size":"7B","Strategy":"KG-Augmented with Supervised Fine-Tuning"}. This record does not assert independent reproduction. ### LLaMA-3.1-8B (SFT) + KG Hits@1: 59.63. Result ID: 69c2ac9047f34ce924abb496. [Reporting paper]() Recorded evaluation configuration: {"Size":"8B","Strategy":"KG-Augmented with Supervised Fine-Tuning"}. This record does not assert independent reproduction. ### Qwen-2.5-7B + KG Hits@1: 56.54. Result ID: 69c2ac9047f34ce924abb490. [Reporting paper]() Recorded evaluation configuration: {"Size":"7B","Strategy":"KG-Augmented without Fine-Tuning"}. This record does not assert independent reproduction. ### GPT-4o Hits@1: 56.2. Result ID: 69c2ac9047f34ce924abb48f. [Reporting paper]() Recorded evaluation configuration: {"Strategy":"LLM Prompting Only"}. This record does not assert independent reproduction. ### LLaMA-3.3-70B Hits@1: 56. Result ID: 69c2ac9047f34ce924abb48c. [Reporting paper]() Recorded evaluation configuration: {"Size":"70B","Strategy":"LLM Prompting Only"}. This record does not assert independent reproduction. ### LLaMA-3.1-8B + KG Hits@1: 55.73. Result ID: 69c2ac9047f34ce924abb491. [Reporting paper]() Recorded evaluation configuration: {"Size":"8B","Strategy":"KG-Augmented without Fine-Tuning"}. This record does not assert independent reproduction. ### GPT-4o-mini Hits@1: 51.98. Result ID: 69c2ac9047f34ce924abb48e. [Reporting paper]() Recorded evaluation configuration: {"Strategy":"LLM Prompting Only"}. This record does not assert independent reproduction. ### DeepSeek-R1-Distill-Llama-70B Hits@1: 43.1. Result ID: 69c2ac9047f34ce924abb48d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"70B","Strategy":"LLM Prompting Only"}. This record does not assert independent reproduction. ### Qwen-2.5-7B Hits@1: 41.88. Result ID: 69c2ac9047f34ce924abb48a. [Reporting paper]() Recorded evaluation configuration: {"Size":"7B","Strategy":"LLM Prompting Only"}. This record does not assert independent reproduction. ### LLaMA-3.1-8B Hits@1: 40.25. Result ID: 69c2ac9047f34ce924abb48b. [Reporting paper]() Recorded evaluation configuration: {"Size":"8B","Strategy":"LLM Prompting Only"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.