# Multihop Question Answering on 2WikiMultiHopQA Out-of-Distribution (Context Scaling) Source: [Multihop Question Answering on 2WikiMultiHopQA Out-of-Distribution (Context Scaling)]() Collection index: [llms.txt]() Data updated: 2026-05-12T15:12:47.487Z Evaluation of Multihop Question Answering performance on the Out-of-Distribution split of 2WikiMultiHopQA, measured across various context window sizes (8K to 1M tokens). 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 | Multihop Question Answering | | Dataset (including any stated split) | 2WikiMultiHopQA Out-of-Distribution | | Metric | Accuracy (8K Context) | | 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 (8K Context)](): Higher is better; unit: PERCENT. - [Accuracy (16K Context)](): Higher is better; unit: PERCENT. - [Accuracy (32K Context)](): Higher is better; unit: PERCENT. - [Accuracy (64K Context)](): Higher is better; unit: PERCENT. - [Accuracy (128K Context)](): Higher is better; unit: PERCENT. - [Accuracy (256K Context)](): Higher is better; unit: PERCENT. - [Accuracy (512K Context)](): Higher is better; unit: PERCENT. - [Accuracy (1M Context)](): Higher is better; unit: PERCENT. - [Average Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy (8K Context) | Result date | Report paper | | --- | --- | --- | --- | | MemReread | 70.3 | Not recorded | 6a02b49edbc836b87d824e59 | | MemAgent | 68 | Not recorded | 6a02b49edbc836b87d824e59 | | ReMemR1 | 64.1 | Not recorded | 6a02b49edbc836b87d824e59 | | MemReread | 37.5 | Not recorded | 6a02b49edbc836b87d824e59 | | ReMemR1 | 35.2 | Not recorded | 6a02b49edbc836b87d824e59 | | MemAgent | 33.6 | Not recorded | 6a02b49edbc836b87d824e59 | ### MemReread Accuracy (8K Context): 70.3. Result ID: 6a03435147f34ce924e852cc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Scale":"4B"}. This record does not assert independent reproduction. ### MemAgent Accuracy (8K Context): 68. Result ID: 6a03435147f34ce924e852ca. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Scale":"4B"}. This record does not assert independent reproduction. ### ReMemR1 Accuracy (8K Context): 64.1. Result ID: 6a03435147f34ce924e852cb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Scale":"4B"}. This record does not assert independent reproduction. ### MemReread Accuracy (8K Context): 37.5. Result ID: 6a03435147f34ce924e852c9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Scale":"1.7B"}. This record does not assert independent reproduction. ### ReMemR1 Accuracy (8K Context): 35.2. Result ID: 6a03435147f34ce924e852c8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Scale":"1.7B"}. This record does not assert independent reproduction. ### MemAgent Accuracy (8K Context): 33.6. Result ID: 6a03435147f34ce924e852c7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Scale":"1.7B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.