# Multi-hop Question Answering on MuSiQue (F1, Token Usage, Compression) Source: [Multi-hop Question Answering on MuSiQue (F1, Token Usage, Compression)]() Collection index: [llms.txt]() Data updated: 2026-04-02T10:26:41.621Z Evaluation of model performance on the MuSiQue dataset for Multi-hop Question Answering, reporting accuracy (F1-score) alongside efficiency metrics related to average token count and percentage token reduction/improvement. 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) | MuSiQue | | Metric | F1 Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 9 of 9 | | 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 - [F1 Score](): Higher is better; unit: PERCENT. - [Avg Token Usage](): Lower is better; unit: SCALAR. - [Token Improvement (%)](): Higher is better; unit: PERCENT. - [Token Reduction (%)](): Higher is better; unit: PERCENT. ## Recorded results | Method | F1 Score | Result date | Report paper | | --- | --- | --- | --- | | OrgAgent | 68.98 | Not recorded | 69cdf81d0636e5bf4afccb65 | | OrgAgent | 57.58 | Not recorded | 69cdf81d0636e5bf4afccb65 | | GPT-5mini | 51.28 | Not recorded | 69cdf81d0636e5bf4afccb65 | | GPT-5mini | 50.31 | Not recorded | 69cdf81d0636e5bf4afccb65 | | GPT-OSS-120B | 48.4 | Not recorded | 69cdf81d0636e5bf4afccb65 | | GPT-OSS-120B | 37.98 | Not recorded | 69cdf81d0636e5bf4afccb65 | | OrgAgent | 32.59 | Not recorded | 69cdf81d0636e5bf4afccb65 | | LLaMA-3.1-8B | 14.55 | Not recorded | 69cdf81d0636e5bf4afccb65 | | LLaMA-3.1-8B | 11.52 | Not recorded | 69cdf81d0636e5bf4afccb65 | ### OrgAgent F1 Score: 68.98. Result ID: 69ce445347f34ce924b81f96. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-5mini","Organization":"Hierarchical (AUTO)"}. This record does not assert independent reproduction. ### OrgAgent F1 Score: 57.58. Result ID: 69ce445347f34ce924b81f99. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-OSS-120B","Organization":"Hierarchical (AUTO)"}. This record does not assert independent reproduction. ### GPT-5mini F1 Score: 51.28. Result ID: 69ce445347f34ce924b81f94. [Reporting paper]() Recorded evaluation configuration: {"Organization":"Baseline"}. This record does not assert independent reproduction. ### GPT-5mini F1 Score: 50.31. Result ID: 69ce445347f34ce924b81f95. [Reporting paper]() Recorded evaluation configuration: {"Organization":"Flat"}. This record does not assert independent reproduction. ### GPT-OSS-120B F1 Score: 48.4. Result ID: 69ce445347f34ce924b81f98. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Organization":"Flat"}. This record does not assert independent reproduction. ### GPT-OSS-120B F1 Score: 37.98. Result ID: 69ce445347f34ce924b81f97. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Organization":"Baseline"}. This record does not assert independent reproduction. ### OrgAgent F1 Score: 32.59. Result ID: 69ce445347f34ce924b81f9c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LLaMA-3.1-8B","Organization":"Hierarchical (AUTO)"}. This record does not assert independent reproduction. ### LLaMA-3.1-8B F1 Score: 14.55. Result ID: 69ce445347f34ce924b81f9b. [Reporting paper]() Recorded evaluation configuration: {"Organization":"Flat"}. This record does not assert independent reproduction. ### LLaMA-3.1-8B F1 Score: 11.52. Result ID: 69ce445347f34ce924b81f9a. [Reporting paper]() Recorded evaluation configuration: {"Organization":"Baseline"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.