# Question Answering on HotpotQA (F1) Source: [Question Answering on HotpotQA (F1)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:43:31.679Z Evaluation of model performance on the HotpotQA dataset for Question Answering, measured using the F1 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 | Question Answering | | Dataset (including any stated split) | HotpotQA | | Metric | F1 Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 36 of 36 | | 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. ## Recorded results | Method | F1 Score | Result date | Report paper | | --- | --- | --- | --- | | Oracle | 69.5 | Not recorded | 697846b2a2b28e761d87c603 | | Oracle | 69.5 | Not recorded | 697846b2a2b28e761d87c603 | | Oracle | 68.7 | Not recorded | 697846b2a2b28e761d87c603 | | Oracle | 68.6 | Not recorded | 697846b2a2b28e761d87c603 | | Oracle | 67.7 | Not recorded | 697846b2a2b28e761d87c603 | | Oracle | 67.5 | Not recorded | 697846b2a2b28e761d87c603 | | DF-RAG + IC | 62.1 | Not recorded | 697846b2a2b28e761d87c603 | | DF-RAG + IC | 61.8 | Not recorded | 697846b2a2b28e761d87c603 | | DF-RAG | 61.8 | Not recorded | 697846b2a2b28e761d87c603 | | DF-RAG + IC | 60.9 | Not recorded | 697846b2a2b28e761d87c603 | | DF-RAG | 60.4 | Not recorded | 697846b2a2b28e761d87c603 | | DF-RAG | 60.3 | Not recorded | 697846b2a2b28e761d87c603 | | DF-RAG + IC | 60.1 | Not recorded | 697846b2a2b28e761d87c603 | | RAG with gMMR | 60.1 | Not recorded | 697846b2a2b28e761d87c603 | | DF-RAG | 59.6 | Not recorded | 697846b2a2b28e761d87c603 | | DF-RAG | 58.5 | Not recorded | 697846b2a2b28e761d87c603 | | DF-RAG + IC | 58.4 | Not recorded | 697846b2a2b28e761d87c603 | | DF-RAG | 58.1 | Not recorded | 697846b2a2b28e761d87c603 | | RAG with gMMR | 58.1 | Not recorded | 697846b2a2b28e761d87c603 | | Vanilla RAG | 57.9 | Not recorded | 697846b2a2b28e761d87c603 | | LongRAG | 57.7 | Not recorded | 697846b2a2b28e761d87c603 | | LongRAG | 57.4 | Not recorded | 697846b2a2b28e761d87c603 | | DF-RAG + IC | 56.8 | Not recorded | 697846b2a2b28e761d87c603 | | RAG with gMMR | 56.7 | Not recorded | 697846b2a2b28e761d87c603 | | Vanilla RAG | 56.1 | Not recorded | 697846b2a2b28e761d87c603 | | Vanilla RAG | 56 | Not recorded | 697846b2a2b28e761d87c603 | | RAG with gMMR | 56 | Not recorded | 697846b2a2b28e761d87c603 | | Vanilla RAG | 55.9 | Not recorded | 697846b2a2b28e761d87c603 | | RAG with gMMR | 55 | Not recorded | 697846b2a2b28e761d87c603 | | RAPTOR | 54.5 | Not recorded | 697846b2a2b28e761d87c603 | | RAG with gMMR | 53.3 | Not recorded | 697846b2a2b28e761d87c603 | | RAPTOR | 53 | Not recorded | 697846b2a2b28e761d87c603 | | Vanilla RAG | 51.2 | Not recorded | 697846b2a2b28e761d87c603 | | Vanilla RAG | 51.1 | Not recorded | 697846b2a2b28e761d87c603 | | HippoRAG | 47 | Not recorded | 697846b2a2b28e761d87c603 | | HippoRAG | 46.2 | Not recorded | 697846b2a2b28e761d87c603 | ### Oracle F1 Score: 69.5. Result ID: 699670375698665ec4b74583. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama 3.3 70B","Context Length":"500 words"}. This record does not assert independent reproduction. ### Oracle F1 Score: 69.5. Result ID: 699670375698665ec4b74597. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama 3.3 70B","Context Length":"1500 words"}. This record does not assert independent reproduction. ### Oracle F1 Score: 68.7. Result ID: 699670375698665ec4b7459c. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen 2.5 72B","Context Length":"1500 words"}. This record does not assert independent reproduction. ### Oracle F1 Score: 68.6. Result ID: 699670375698665ec4b7458d. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama 3.3 70B","Context Length":"1000 words"}. This record does not assert independent reproduction. ### Oracle F1 Score: 67.7. Result ID: 699670375698665ec4b74588. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen 2.5 72B","Context Length":"500 words"}. This record does not assert independent reproduction. ### Oracle F1 Score: 67.5. Result ID: 699670375698665ec4b74592. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen 2.5 72B","Context Length":"1000 words"}. This record does not assert independent reproduction. ### DF-RAG + IC F1 Score: 62.1. Result ID: 699670375698665ec4b74596. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen 2.5 72B","Context Length":"1000 words"}. This record does not assert independent reproduction. ### DF-RAG + IC F1 Score: 61.8. Result ID: 699670375698665ec4b7459b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama 3.3 70B","Context Length":"1500 words"}. This record does not assert independent reproduction. ### DF-RAG F1 Score: 61.8. Result ID: 699670375698665ec4b7459f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen 2.5 72B","Context Length":"1500 words"}. This record does not assert independent reproduction. ### DF-RAG + IC F1 Score: 60.9. Result ID: 699670375698665ec4b745a0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen 2.5 72B","Context Length":"1500 words"}. This record does not assert independent reproduction. ### DF-RAG F1 Score: 60.4. Result ID: 699670375698665ec4b74595. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen 2.5 72B","Context Length":"1000 words"}. This record does not assert independent reproduction. ### DF-RAG F1 Score: 60.3. Result ID: 699670375698665ec4b74590. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama 3.3 70B","Context Length":"1000 words"}. This record does not assert independent reproduction. ### DF-RAG + IC F1 Score: 60.1. Result ID: 699670375698665ec4b7458c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen 2.5 72B","Context Length":"500 words"}. This record does not assert independent reproduction. ### RAG with gMMR F1 Score: 60.1. Result ID: 699670375698665ec4b7459e. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen 2.5 72B","Context Length":"1500 words"}. This record does not assert independent reproduction. ### DF-RAG F1 Score: 59.6. Result ID: 699670375698665ec4b7459a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama 3.3 70B","Context Length":"1500 words"}. This record does not assert independent reproduction. ### DF-RAG F1 Score: 58.5. Result ID: 699670375698665ec4b7458b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen 2.5 72B","Context Length":"500 words"}. This record does not assert independent reproduction. ### DF-RAG + IC F1 Score: 58.4. Result ID: 699670375698665ec4b74591. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama 3.3 70B","Context Length":"1000 words"}. This record does not assert independent reproduction. ### DF-RAG F1 Score: 58.1. Result ID: 699670375698665ec4b74586. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama 3.3 70B","Context Length":"500 words"}. This record does not assert independent reproduction. ### RAG with gMMR F1 Score: 58.1. Result ID: 699670375698665ec4b74599. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama 3.3 70B","Context Length":"1500 words"}. This record does not assert independent reproduction. ### Vanilla RAG F1 Score: 57.9. Result ID: 699670375698665ec4b7459d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen 2.5 72B","Context Length":"1500 words"}. This record does not assert independent reproduction. ### LongRAG F1 Score: 57.7. Result ID: 699670375698665ec4b745a2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen 2.5 72B","Context Length":"independent"}. This record does not assert independent reproduction. ### LongRAG F1 Score: 57.4. Result ID: 699670375698665ec4b745a1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama 3.3 70B","Context Length":"independent"}. This record does not assert independent reproduction. ### DF-RAG + IC F1 Score: 56.8. Result ID: 699670375698665ec4b74587. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama 3.3 70B","Context Length":"500 words"}. This record does not assert independent reproduction. ### RAG with gMMR F1 Score: 56.7. Result ID: 699670375698665ec4b74594. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen 2.5 72B","Context Length":"1000 words"}. This record does not assert independent reproduction. ### Vanilla RAG F1 Score: 56.1. Result ID: 699670375698665ec4b74598. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Llama 3.3 70B","Context Length":"1500 words"}. This record does not assert independent reproduction. ### Vanilla RAG F1 Score: 56. Result ID: 699670375698665ec4b7458e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Llama 3.3 70B","Context Length":"1000 words"}. This record does not assert independent reproduction. ### RAG with gMMR F1 Score: 56. Result ID: 699670375698665ec4b7458f. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama 3.3 70B","Context Length":"1000 words"}. This record does not assert independent reproduction. ### Vanilla RAG F1 Score: 55.9. Result ID: 699670375698665ec4b74593. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen 2.5 72B","Context Length":"1000 words"}. This record does not assert independent reproduction. ### RAG with gMMR F1 Score: 55. Result ID: 699670375698665ec4b7458a. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen 2.5 72B","Context Length":"500 words"}. This record does not assert independent reproduction. ### RAPTOR F1 Score: 54.5. Result ID: 699670375698665ec4b745a3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama 3.3 70B","Context Length":"independent"}. This record does not assert independent reproduction. ### RAG with gMMR F1 Score: 53.3. Result ID: 699670375698665ec4b74585. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama 3.3 70B","Context Length":"500 words"}. This record does not assert independent reproduction. ### RAPTOR F1 Score: 53. Result ID: 699670375698665ec4b745a4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen 2.5 72B","Context Length":"independent"}. This record does not assert independent reproduction. ### Vanilla RAG F1 Score: 51.2. Result ID: 699670375698665ec4b74589. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen 2.5 72B","Context Length":"500 words"}. This record does not assert independent reproduction. ### Vanilla RAG F1 Score: 51.1. Result ID: 699670375698665ec4b74584. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Llama 3.3 70B","Context Length":"500 words"}. This record does not assert independent reproduction. ### HippoRAG F1 Score: 47. Result ID: 699670375698665ec4b745a6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen 2.5 72B","Context Length":"independent"}. This record does not assert independent reproduction. ### HippoRAG F1 Score: 46.2. Result ID: 699670375698665ec4b745a5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama 3.3 70B","Context Length":"independent"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.