# Reading Comprehension on QuALITY (Accuracy) Source: [Reading Comprehension on QuALITY (Accuracy)]() Collection index: [llms.txt]() Data updated: 2026-06-17T08:01:47.558Z Evaluation of reading comprehension models on the QuALITY dataset, specifically measured using the Accuracy metric. 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 | Reading Comprehension | | Dataset (including any stated split) | QuALITY | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 26 of 26 | | 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. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | EraRAG | 61.78 | Not recorded | 6a322a5ad33dfb23e783eda0 | | RAPTOR | 60.87 | Not recorded | 6a322a5ad33dfb23e783eda0 | | EraRAG | 60.79 | Not recorded | 6a322a5ad33dfb23e783eda0 | | HyGRAG | 60.67 | Not recorded | 6a322a5ad33dfb23e783eda0 | | HyGRAG +Inference | 59.79 | Not recorded | 6a322a5ad33dfb23e783eda0 | | HyGRAG | 59.49 | Not recorded | 6a322a5ad33dfb23e783eda0 | | VanillaRAG | 59.28 | Not recorded | 6a322a5ad33dfb23e783eda0 | | L-GraphRAG | 58.75 | Not recorded | 6a322a5ad33dfb23e783eda0 | | L-LightRAG | 58.41 | Not recorded | 6a322a5ad33dfb23e783eda0 | | RAPTOR-K | 58.34 | Not recorded | 6a322a5ad33dfb23e783eda0 | | RAPTOR | 58.08 | Not recorded | 6a322a5ad33dfb23e783eda0 | | HippoRAG | 56.65 | Not recorded | 6a322a5ad33dfb23e783eda0 | | VanillaRAG | 56.38 | Not recorded | 6a322a5ad33dfb23e783eda0 | | HiRAG | 55.83 | Not recorded | 6a322a5ad33dfb23e783eda0 | | L-GraphRAG | 50.01 | Not recorded | 6a322a5ad33dfb23e783eda0 | | L-LightRAG | 48.05 | Not recorded | 6a322a5ad33dfb23e783eda0 | | HippoRAG | 46.1 | Not recorded | 6a322a5ad33dfb23e783eda0 | | HippoRAG2 | 45.98 | Not recorded | 6a322a5ad33dfb23e783eda0 | | HippoRAG2 | 42.53 | Not recorded | 6a322a5ad33dfb23e783eda0 | | H-LightRAG | 38.6 | Not recorded | 6a322a5ad33dfb23e783eda0 | | ArchRAG | 37.77 | Not recorded | 6a322a5ad33dfb23e783eda0 | | CoT | 36.06 | Not recorded | 6a322a5ad33dfb23e783eda0 | | Zero-shot | 34.78 | Not recorded | 6a322a5ad33dfb23e783eda0 | | CoT | 33.83 | Not recorded | 6a322a5ad33dfb23e783eda0 | | Zero-shot | 33.54 | Not recorded | 6a322a5ad33dfb23e783eda0 | | G-LightRAG | 30.53 | Not recorded | 6a322a5ad33dfb23e783eda0 | ### EraRAG Accuracy: 61.78. Result ID: 6a3253c1fbc373592c2fb092. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base LLM":"Qwen3-8B"}. This record does not assert independent reproduction. ### RAPTOR Accuracy: 60.87. Result ID: 6a3253c1fbc373592c2fb091. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base LLM":"Qwen3-8B"}. This record does not assert independent reproduction. ### EraRAG Accuracy: 60.79. Result ID: 6a3253c1fbc373592c2fb0c5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### HyGRAG Accuracy: 60.67. Result ID: 6a3253c1fbc373592c2fb097. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base LLM":"Qwen3-8B"}. This record does not assert independent reproduction. ### HyGRAG +Inference Accuracy: 59.79. Result ID: 6a3253c1fbc373592c2fb0cf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### HyGRAG Accuracy: 59.49. Result ID: 6a3253c1fbc373592c2fb0ce. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### VanillaRAG Accuracy: 59.28. Result ID: 6a3253c1fbc373592c2fb090. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Base LLM":"Qwen3-8B"}. This record does not assert independent reproduction. ### L-GraphRAG Accuracy: 58.75. Result ID: 6a3253c1fbc373592c2fb096. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base LLM":"Qwen3-8B"}. This record does not assert independent reproduction. ### L-LightRAG Accuracy: 58.41. Result ID: 6a3253c1fbc373592c2fb093. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base LLM":"Qwen3-8B"}. This record does not assert independent reproduction. ### RAPTOR-K Accuracy: 58.34. Result ID: 6a3253c1fbc373592c2fb0c4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### RAPTOR Accuracy: 58.08. Result ID: 6a3253c1fbc373592c2fb0c3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### HippoRAG Accuracy: 56.65. Result ID: 6a3253c1fbc373592c2fb094. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base LLM":"Qwen3-8B"}. This record does not assert independent reproduction. ### VanillaRAG Accuracy: 56.38. Result ID: 6a3253c1fbc373592c2fb0c2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### HiRAG Accuracy: 55.83. Result ID: 6a3253c1fbc373592c2fb0cc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### L-GraphRAG Accuracy: 50.01. Result ID: 6a3253c1fbc373592c2fb0cb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### L-LightRAG Accuracy: 48.05. Result ID: 6a3253c1fbc373592c2fb0c6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### HippoRAG Accuracy: 46.1. Result ID: 6a3253c1fbc373592c2fb0c9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### HippoRAG2 Accuracy: 45.98. Result ID: 6a3253c1fbc373592c2fb0ca. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### HippoRAG2 Accuracy: 42.53. Result ID: 6a3253c1fbc373592c2fb095. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base LLM":"Qwen3-8B"}. This record does not assert independent reproduction. ### H-LightRAG Accuracy: 38.6. Result ID: 6a3253c1fbc373592c2fb0c8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### ArchRAG Accuracy: 37.77. Result ID: 6a3253c1fbc373592c2fb0cd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### CoT Accuracy: 36.06. Result ID: 6a3253c1fbc373592c2fb08f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Base LLM":"Qwen3-8B"}. This record does not assert independent reproduction. ### Zero-shot Accuracy: 34.78. Result ID: 6a3253c1fbc373592c2fb08e. [Reporting paper]() Recorded evaluation configuration: {"Base LLM":"Qwen3-8B"}. This record does not assert independent reproduction. ### CoT Accuracy: 33.83. Result ID: 6a3253c1fbc373592c2fb0c1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### Zero-shot Accuracy: 33.54. Result ID: 6a3253c1fbc373592c2fb0c0. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### G-LightRAG Accuracy: 30.53. Result ID: 6a3253c1fbc373592c2fb0c7. [Reporting paper]() [Method origin 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.