# Multi-document Multi-entity Question Answering on Loong (50K-100K Tokens) Source: [Multi-document Multi-entity Question Answering on Loong (50K-100K Tokens)]() Collection index: [llms.txt]() Data updated: 2026-03-13T08:53:20.476Z Evaluation of model performance on the specific 50K-100K token subset of the Loong dataset for Multi-document Multi-entity Question Answering, reporting detailed scores across Spotlight Locating, Comparison, Clustering, Chain of Reason, and Overall components. 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-document Multi-entity Question Answering | | Dataset (including any stated split) | Loong (50K-100K Tokens) | | Metric | Spotlight Locating Score (Avg) | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 5 of 5 | | 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 - [Spotlight Locating Score (Avg)](): Higher is better; unit: SCALAR. - [Spotlight Locating Rate (Perfect)](): Higher is better; unit: PERCENT. - [Comparison Score (Avg)](): Higher is better; unit: SCALAR. - [Comparison Rate (Perfect)](): Higher is better; unit: PERCENT. - [Clustering Score (Avg)](): Higher is better; unit: SCALAR. - [Clustering Rate (Perfect)](): Higher is better; unit: PERCENT. - [Chain of Reason Score (Avg)](): Higher is better; unit: SCALAR. - [Chain of Reason Rate (Perfect)](): Higher is better; unit: PERCENT. - [Overall Score (Avg)](): Higher is better; unit: SCALAR. - [Overall Rate (Perfect)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Spotlight Locating Score (Avg) | Result date | Report paper | | --- | --- | --- | --- | | DocSage | 88.79 | Not recorded | 69b39a210636e5bf4afbcb2c | | GPT-4o | 88.5 | Not recorded | 69b39a210636e5bf4afbcb2c | | StructRAG | 69.36 | Not recorded | 69b39a210636e5bf4afbcb2c | | GPT-4o + RAG | 67.6 | Not recorded | 69b39a210636e5bf4afbcb2c | | GraphRAG | 24.55 | Not recorded | 69b39a210636e5bf4afbcb2c | ### DocSage Spotlight Locating Score (Avg): 88.79. Result ID: 69b3d07047f34ce9249e0668. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method":"DocSage (Ours)"}. This record does not assert independent reproduction. ### GPT-4o Spotlight Locating Score (Avg): 88.5. Result ID: 69b3d07047f34ce9249e0664. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Method":"GPT-4o"}. This record does not assert independent reproduction. ### StructRAG Spotlight Locating Score (Avg): 69.36. Result ID: 69b3d07047f34ce9249e0667. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method":"StructRAG"}. This record does not assert independent reproduction. ### GPT-4o + RAG Spotlight Locating Score (Avg): 67.6. Result ID: 69b3d07047f34ce9249e0665. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Method":"GPT-4o + RAG"}. This record does not assert independent reproduction. ### GraphRAG Spotlight Locating Score (Avg): 24.55. Result ID: 69b3d07047f34ce9249e0666. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method":"GraphRAG"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.