# Open-domain Question Answering on NaturalQuestions standard (test) Source: [Open-domain Question Answering on NaturalQuestions standard (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:30:50.468Z Evaluation of model performance on the standard test split of the NaturalQuestions dataset for Open-domain Question Answering, measured using Accuracy. 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 | Open-domain Question Answering | | Dataset (including any stated split) | NaturalQuestions standard (test) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 12 of 12 | | 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 - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Ours (theory-guided context selection strategy) | 45.5 | Not recorded | 698abbd5c97a0b3e3b5de20c | | ReMem | 45.3 | Not recorded | 698abbd5c97a0b3e3b5de20c | | ExpRAG | 45.1 | Not recorded | 698abbd5c97a0b3e3b5de20c | | DC | 45 | Not recorded | 698abbd5c97a0b3e3b5de20c | | BM25 | 44.6 | Not recorded | 698abbd5c97a0b3e3b5de20c | | Zero | 44.2 | Not recorded | 698abbd5c97a0b3e3b5de20c | | ReMem | 39.8 | Not recorded | 698abbd5c97a0b3e3b5de20c | | Ours (theory-guided context selection strategy) | 39.7 | Not recorded | 698abbd5c97a0b3e3b5de20c | | ExpRAG | 39.4 | Not recorded | 698abbd5c97a0b3e3b5de20c | | DC | 39.3 | Not recorded | 698abbd5c97a0b3e3b5de20c | | BM25 | 38.9 | Not recorded | 698abbd5c97a0b3e3b5de20c | | Zero | 38.5 | Not recorded | 698abbd5c97a0b3e3b5de20c | ### Ours (theory-guided context selection strategy) Accuracy: 45.5. Result ID: 6996402f5698665ec4838905. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-8B"}. This record does not assert independent reproduction. ### ReMem Accuracy: 45.3. Result ID: 6996402f5698665ec4838904. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-8B"}. This record does not assert independent reproduction. ### ExpRAG Accuracy: 45.1. Result ID: 6996402f5698665ec4838903. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-8B"}. This record does not assert independent reproduction. ### DC Accuracy: 45. Result ID: 6996402f5698665ec4838902. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-8B"}. This record does not assert independent reproduction. ### BM25 Accuracy: 44.6. Result ID: 6996402f5698665ec4838901. [Reporting paper]() Recorded evaluation configuration: {"Model":"Qwen3-8B"}. This record does not assert independent reproduction. ### Zero Accuracy: 44.2. Result ID: 6996402f5698665ec4838900. [Reporting paper]() Recorded evaluation configuration: {"Model":"Qwen3-8B"}. This record does not assert independent reproduction. ### ReMem Accuracy: 39.8. Result ID: 6996402f5698665ec48388fe. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama-3.1-8B"}. This record does not assert independent reproduction. ### Ours (theory-guided context selection strategy) Accuracy: 39.7. Result ID: 6996402f5698665ec48388ff. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama-3.1-8B"}. This record does not assert independent reproduction. ### ExpRAG Accuracy: 39.4. Result ID: 6996402f5698665ec48388fd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama-3.1-8B"}. This record does not assert independent reproduction. ### DC Accuracy: 39.3. Result ID: 6996402f5698665ec48388fc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama-3.1-8B"}. This record does not assert independent reproduction. ### BM25 Accuracy: 38.9. Result ID: 6996402f5698665ec48388fb. [Reporting paper]() Recorded evaluation configuration: {"Model":"Llama-3.1-8B"}. This record does not assert independent reproduction. ### Zero Accuracy: 38.5. Result ID: 6996402f5698665ec48388fa. [Reporting paper]() Recorded evaluation configuration: {"Model":"Llama-3.1-8B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.