# Long-context Question Answering on MuSiQue (Passage Split) Source: [Long-context Question Answering on MuSiQue (Passage Split)]() Collection index: [llms.txt]() Data updated: 2026-03-06T09:56:50.261Z Evaluation of model performance on the Passage Split of the MuSiQue dataset for Long-context Question Answering tasks, measured by Score. 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 | Long-context Question Answering | | Dataset (including any stated split) | MuSiQue (Passage Split) | | Metric | Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 18 of 18 | | 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 - [Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Score | Result date | Report paper | | --- | --- | --- | --- | | Baseline | 39.46 | Not recorded | 69aa5f972d603e6de3e41a04 | | Our | 37.58 | Not recorded | 69aa5f972d603e6de3e41a04 | | Baseline | 37.18 | Not recorded | 69aa5f972d603e6de3e41a04 | | Our + Reorder | 36.35 | Not recorded | 69aa5f972d603e6de3e41a04 | | Our | 33.86 | Not recorded | 69aa5f972d603e6de3e41a04 | | Our + Reorder | 32.85 | Not recorded | 69aa5f972d603e6de3e41a04 | | Baseline | 32.85 | Not recorded | 69aa5f972d603e6de3e41a04 | | CacheBlend | 31.88 | Not recorded | 69aa5f972d603e6de3e41a04 | | EPIC (15%) | 30.91 | Not recorded | 69aa5f972d603e6de3e41a04 | | Our | 29.96 | Not recorded | 69aa5f972d603e6de3e41a04 | | EPIC (15%) | 28.52 | Not recorded | 69aa5f972d603e6de3e41a04 | | Our + Reorder | 27.93 | Not recorded | 69aa5f972d603e6de3e41a04 | | CacheBlend | 27.65 | Not recorded | 69aa5f972d603e6de3e41a04 | | CacheBlend | 27.08 | Not recorded | 69aa5f972d603e6de3e41a04 | | EPIC (15%) | 24.8 | Not recorded | 69aa5f972d603e6de3e41a04 | | No Recompute | 24.74 | Not recorded | 69aa5f972d603e6de3e41a04 | | No Recompute | 24.62 | Not recorded | 69aa5f972d603e6de3e41a04 | | No Recompute | 10.12 | Not recorded | 69aa5f972d603e6de3e41a04 | ### Baseline Score: 39.46. Result ID: 69aaa4d76dbb7075b954d3c7. [Reporting paper]() Recorded evaluation configuration: {"Model":"ChatGLM","Setting":"Passage Split"}. This record does not assert independent reproduction. ### Our Score: 37.58. Result ID: 69aaa4d76dbb7075b954d3c9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ChatGLM","Setting":"Passage Split"}. This record does not assert independent reproduction. ### Baseline Score: 37.18. Result ID: 69aaa4d76dbb7075b954d3bb. [Reporting paper]() Recorded evaluation configuration: {"Model":"Qwen","Setting":"Passage Split"}. This record does not assert independent reproduction. ### Our + Reorder Score: 36.35. Result ID: 69aaa4d76dbb7075b954d3ca. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ChatGLM","Setting":"Passage Split"}. This record does not assert independent reproduction. ### Our Score: 33.86. Result ID: 69aaa4d76dbb7075b954d3bd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen","Setting":"Passage Split"}. This record does not assert independent reproduction. ### Our + Reorder Score: 32.85. Result ID: 69aaa4d76dbb7075b954d3be. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen","Setting":"Passage Split"}. This record does not assert independent reproduction. ### Baseline Score: 32.85. Result ID: 69aaa4d76dbb7075b954d3c1. [Reporting paper]() Recorded evaluation configuration: {"Model":"LLaMA","Setting":"Passage Split"}. This record does not assert independent reproduction. ### CacheBlend Score: 31.88. Result ID: 69aaa4d76dbb7075b954d3cb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ChatGLM","Setting":"Passage Split"}. This record does not assert independent reproduction. ### EPIC (15%) Score: 30.91. Result ID: 69aaa4d76dbb7075b954d3cc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ChatGLM","Setting":"Passage Split"}. This record does not assert independent reproduction. ### Our Score: 29.96. Result ID: 69aaa4d76dbb7075b954d3c3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LLaMA","Setting":"Passage Split"}. This record does not assert independent reproduction. ### EPIC (15%) Score: 28.52. Result ID: 69aaa4d76dbb7075b954d3c6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LLaMA","Setting":"Passage Split"}. This record does not assert independent reproduction. ### Our + Reorder Score: 27.93. Result ID: 69aaa4d76dbb7075b954d3c4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LLaMA","Setting":"Passage Split"}. This record does not assert independent reproduction. ### CacheBlend Score: 27.65. Result ID: 69aaa4d76dbb7075b954d3bf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen","Setting":"Passage Split"}. This record does not assert independent reproduction. ### CacheBlend Score: 27.08. Result ID: 69aaa4d76dbb7075b954d3c5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LLaMA","Setting":"Passage Split"}. This record does not assert independent reproduction. ### EPIC (15%) Score: 24.8. Result ID: 69aaa4d76dbb7075b954d3c0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen","Setting":"Passage Split"}. This record does not assert independent reproduction. ### No Recompute Score: 24.74. Result ID: 69aaa4d76dbb7075b954d3c8. [Reporting paper]() Recorded evaluation configuration: {"Model":"ChatGLM","Setting":"Passage Split"}. This record does not assert independent reproduction. ### No Recompute Score: 24.62. Result ID: 69aaa4d76dbb7075b954d3c2. [Reporting paper]() Recorded evaluation configuration: {"Model":"LLaMA","Setting":"Passage Split"}. This record does not assert independent reproduction. ### No Recompute Score: 10.12. Result ID: 69aaa4d76dbb7075b954d3bc. [Reporting paper]() Recorded evaluation configuration: {"Model":"Qwen","Setting":"Passage Split"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.