# Multi-hop Question Answering on HotpotQA (Accuracy and Avg. Tokens) Source: [Multi-hop Question Answering on HotpotQA (Accuracy and Avg. Tokens)]() Collection index: [llms.txt]() Data updated: 2026-03-09T07:34:46.130Z Evaluation of model performance on the HotpotQA dataset for multi-hop question answering, reporting standard accuracy and the average length of generated 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 | Multi-hop Question Answering | | Dataset (including any stated split) | HotpotQA | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 15 of 15 | | 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. - [Average Tokens](): Higher is better; unit: SCALAR. - [Average Input Tokens](): Higher is better; unit: SCALAR. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | RouteGoT | 88 | Not recorded | 69ae53fd2d603e6de3e42b01 | | GoT\* | 87 | Not recorded | 69ae53fd2d603e6de3e42b01 | | CoT | 86 | Not recorded | 69ae53fd2d603e6de3e42b01 | | RouteLLM | 83 | Not recorded | 69ae53fd2d603e6de3e42b01 | | IO | 81 | Not recorded | 69ae53fd2d603e6de3e42b01 | | KNN | 79 | Not recorded | 69ae53fd2d603e6de3e42b01 | | RTR | 79 | Not recorded | 69ae53fd2d603e6de3e42b01 | | Random | 77 | Not recorded | 69ae53fd2d603e6de3e42b01 | | EmbedLLM | 77 | Not recorded | 69ae53fd2d603e6de3e42b01 | | AGoT | 72 | Not recorded | 69ae53fd2d603e6de3e42b01 | | ACE | 62.8 | Not recorded | 6967232ce25ad2fa9d1ec2bb | | ToT | 60 | Not recorded | 69ae53fd2d603e6de3e42b01 | | RAG | 38.9 | Not recorded | 6967232ce25ad2fa9d1ec2bb | | IterDRAG | 38.9 | Not recorded | 6967232ce25ad2fa9d1ec2bb | | Vanilla | 25.7 | Not recorded | 6967232ce25ad2fa9d1ec2bb | ### RouteGoT Accuracy: 88. Result ID: 69ae78076dbb7075b9563de6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Pool":"{Qwen3-4B, 8B, 30B}"}. This record does not assert independent reproduction. ### GoT\* Accuracy: 87. Result ID: 69ae78076dbb7075b9563ddf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-30B"}. This record does not assert independent reproduction. ### CoT Accuracy: 86. Result ID: 69ae78076dbb7075b9563ddd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-30B"}. This record does not assert independent reproduction. ### RouteLLM Accuracy: 83. Result ID: 69ae78076dbb7075b9563de3. [Reporting paper]() Recorded evaluation configuration: {"Model Pool":"{Qwen3-4B, 8B, 30B}"}. This record does not assert independent reproduction. ### IO Accuracy: 81. Result ID: 69ae78076dbb7075b9563ddc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-30B"}. This record does not assert independent reproduction. ### KNN Accuracy: 79. Result ID: 69ae78076dbb7075b9563de2. [Reporting paper]() Recorded evaluation configuration: {"Model Pool":"{Qwen3-4B, 8B, 30B}"}. This record does not assert independent reproduction. ### RTR Accuracy: 79. Result ID: 69ae78076dbb7075b9563de5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Pool":"{Qwen3-4B, 8B, 30B}"}. This record does not assert independent reproduction. ### Random Accuracy: 77. Result ID: 69ae78076dbb7075b9563de1. [Reporting paper]() Recorded evaluation configuration: {"Model Pool":"{Qwen3-4B, 8B, 30B}"}. This record does not assert independent reproduction. ### EmbedLLM Accuracy: 77. Result ID: 69ae78076dbb7075b9563de4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Pool":"{Qwen3-4B, 8B, 30B}"}. This record does not assert independent reproduction. ### AGoT Accuracy: 72. Result ID: 69ae78076dbb7075b9563de0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-30B"}. This record does not assert independent reproduction. ### ACE Accuracy: 62.8. Result ID: 6996885a5698665ec4d0d15d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LLaMA-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### ToT Accuracy: 60. Result ID: 69ae78076dbb7075b9563dde. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen3-30B"}. This record does not assert independent reproduction. ### RAG Accuracy: 38.9. Result ID: 6996885a5698665ec4d0d15b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"LLaMA-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### IterDRAG Accuracy: 38.9. Result ID: 6996885a5698665ec4d0d15c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LLaMA-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### Vanilla Accuracy: 25.7. Result ID: 6996885a5698665ec4d0d15a. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"LLaMA-3.1-8B-Instruct"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.