# Single-hop Question Answering on NQ Source: [Single-hop Question Answering on NQ]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:41:41.478Z Evaluation of single-hop question answering performance on the Natural Questions (NQ) dataset, measured using Exact Match (EM) and F1 scores. 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 | Single-hop QA | | Dataset (including any stated split) | NQ | | Metric | EM | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 13 of 13 | | 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 - [EM](): Higher is better; unit: PERCENT. - [F1](): Higher is better; unit: PERCENT. ## Recorded results | Method | EM | Result date | Report paper | | --- | --- | --- | --- | | HELP | 43 | Not recorded | 699e82126017c4460ffacf5f | | HippoRAG2 | 40.4 | Not recorded | 699e82126017c4460ffacf5f | | Llama3.3-70B | 36 | Not recorded | 68fa76911e209131cea6dca9 | | Search-o1 | 34 | Not recorded | 68fa76911e209131cea6dca9 | | RAgent-QwQ-32B | 33.8 | Not recorded | 68fa76911e209131cea6dca9 | | RAG-Qwen2.5-32B | 33.4 | Not recorded | 68fa76911e209131cea6dca9 | | RAgent-Qwen2.5-32B | 32.4 | Not recorded | 68fa76911e209131cea6dca9 | | LinearRAG | 31.6 | Not recorded | 699e82126017c4460ffacf5f | | HyperGraphRAG | 30.3 | Not recorded | 699e82126017c4460ffacf5f | | RAG-QwQ-32B | 29.6 | Not recorded | 68fa76911e209131cea6dca9 | | Qwen2.5-72B | 27.6 | Not recorded | 68fa76911e209131cea6dca9 | | QwQ-32B | 23 | Not recorded | 68fa76911e209131cea6dca9 | | Qwen2.5-32B | 22.8 | Not recorded | 68fa76911e209131cea6dca9 | ### HELP EM: 43. Result ID: 699ebc2c5698665ec48b68ce. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-30B-A3B-Instruct-2507"}. This record does not assert independent reproduction. ### HippoRAG2 EM: 40.4. Result ID: 699ebc2c5698665ec48b68cb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-30B-A3B-Instruct-2507"}. This record does not assert independent reproduction. ### Llama3.3-70B EM: 36. Result ID: 6994598f3a6c3148491cad90. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Reasoning Protocol":"Direct Reasoning (w/o Retrieval)","Parameter Count":"70B"}. This record does not assert independent reproduction. ### Search-o1 EM: 34. Result ID: 6994598f3a6c3148491cad95. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Reasoning Protocol":"Retrieval-augmented Reasoning with Reason-in-Documents","Parameter Count":"32B"}. This record does not assert independent reproduction. ### RAgent-QwQ-32B EM: 33.8. Result ID: 6994598f3a6c3148491cad94. [Reporting paper]() Recorded evaluation configuration: {"Reasoning Protocol":"Retrieval-augmented Reasoning","Parameter Count":"32B"}. This record does not assert independent reproduction. ### RAG-Qwen2.5-32B EM: 33.4. Result ID: 6994598f3a6c3148491cad91. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Reasoning Protocol":"Retrieval-augmented Reasoning","Parameter Count":"32B"}. This record does not assert independent reproduction. ### RAgent-Qwen2.5-32B EM: 32.4. Result ID: 6994598f3a6c3148491cad93. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Reasoning Protocol":"Retrieval-augmented Reasoning","Parameter Count":"32B"}. This record does not assert independent reproduction. ### LinearRAG EM: 31.6. Result ID: 699ebc2c5698665ec48b68cc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-30B-A3B-Instruct-2507"}. This record does not assert independent reproduction. ### HyperGraphRAG EM: 30.3. Result ID: 699ebc2c5698665ec48b68cd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-30B-A3B-Instruct-2507"}. This record does not assert independent reproduction. ### RAG-QwQ-32B EM: 29.6. Result ID: 6994598f3a6c3148491cad92. [Reporting paper]() Recorded evaluation configuration: {"Reasoning Protocol":"Retrieval-augmented Reasoning","Parameter Count":"32B"}. This record does not assert independent reproduction. ### Qwen2.5-72B EM: 27.6. Result ID: 6994598f3a6c3148491cad8f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Reasoning Protocol":"Direct Reasoning (w/o Retrieval)","Parameter Count":"72B"}. This record does not assert independent reproduction. ### QwQ-32B EM: 23. Result ID: 6994598f3a6c3148491cad8e. [Reporting paper]() Recorded evaluation configuration: {"Reasoning Protocol":"Direct Reasoning (w/o Retrieval)","Parameter Count":"32B"}. This record does not assert independent reproduction. ### Qwen2.5-32B EM: 22.8. Result ID: 6994598f3a6c3148491cad8d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Reasoning Protocol":"Direct Reasoning (w/o Retrieval)","Parameter Count":"32B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.