# Multi-hop Question Answering on PopQA Source: [Multi-hop Question Answering on PopQA]() Collection index: [llms.txt]() Data updated: 2026-06-04T08:18:35.193Z Evaluation of model performance on the PopQA dataset specifically for Multi-hop Question Answering tasks, 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 | Multi-hop Question Answering | | Dataset (including any stated split) | PopQA | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 6 of 6 | | 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 | | --- | --- | --- | --- | | Qwen2.5-7B-Instruct + MemTrain + MEM1 | 38.36 | Not recorded | 6a21065ec10484bac23efebf | | Qwen3-4B-Instruct-2507 + MemTrain + MEM1 | 37.91 | Not recorded | 6a21065ec10484bac23efebf | | Qwen2.5-7B-Instruct + MEM1 | 27.13 | Not recorded | 6a21065ec10484bac23efebf | | Qwen3-4B-Instruct-2507 + MEM1 | 23.62 | Not recorded | 6a21065ec10484bac23efebf | | Qwen3-4B-Instruct-2507 | 21.81 | Not recorded | 6a21065ec10484bac23efebf | | Qwen2.5-7B-Instruct | 12.59 | Not recorded | 6a21065ec10484bac23efebf | ### Qwen2.5-7B-Instruct + MemTrain + MEM1 Accuracy: 38.36. Result ID: 6a213331fbc373592c1ca44d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct","Memory Tool":"MEM1","Training":"MemTrain"}. This record does not assert independent reproduction. ### Qwen3-4B-Instruct-2507 + MemTrain + MEM1 Accuracy: 37.91. Result ID: 6a213331fbc373592c1ca44a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B-Instruct-2507","Memory Tool":"MEM1","Training":"MemTrain"}. This record does not assert independent reproduction. ### Qwen2.5-7B-Instruct + MEM1 Accuracy: 27.13. Result ID: 6a213331fbc373592c1ca44c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct","Memory Tool":"MEM1"}. This record does not assert independent reproduction. ### Qwen3-4B-Instruct-2507 + MEM1 Accuracy: 23.62. Result ID: 6a213331fbc373592c1ca449. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B-Instruct-2507","Memory Tool":"MEM1"}. This record does not assert independent reproduction. ### Qwen3-4B-Instruct-2507 Accuracy: 21.81. Result ID: 6a213331fbc373592c1ca448. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B-Instruct-2507"}. This record does not assert independent reproduction. ### Qwen2.5-7B-Instruct Accuracy: 12.59. Result ID: 6a213331fbc373592c1ca44b. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.