# Open-domain Question Answering on TriviaQA (TQA) Source: [Open-domain Question Answering on TriviaQA (TQA)]() Collection index: [llms.txt]() Data updated: 2026-03-18T07:02:31.270Z Evaluation of Open-domain Question Answering performance on the TriviaQA dataset, reporting Accuracy and 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 | Open-domain Question Answering | | Dataset (including any stated split) | TriviaQA (TQA) | | Metric | Accuracy | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 28 of 28 | | 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: SCALAR. - [F1 Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | UR-RAG | 0.4177 | Not recorded | 6979984ea2b28e761d87cd2d | | RePlug | 0.401 | Not recorded | 6979984ea2b28e761d87cd2d | | LURE-RAG (w/o topics) | 0.401 | Not recorded | 6979984ea2b28e761d87cd2d | | LURE-RAG | 0.3994 | Not recorded | 6979984ea2b28e761d87cd2d | | Gemma3 1B | 0.398 | Not recorded | 69ba317b0636e5bf4afc071e | | k-shot | 0.3966 | Not recorded | 6979984ea2b28e761d87cd2d | | UR-RAG | 0.3699 | Not recorded | 6979984ea2b28e761d87cd2d | | LURE-RAG | 0.3635 | Not recorded | 6979984ea2b28e761d87cd2d | | LURE-RAG (w/o topics) | 0.3628 | Not recorded | 6979984ea2b28e761d87cd2d | | MobileLLM-Flash 1.4B | 0.3606 | Not recorded | 69ba317b0636e5bf4afc071e | | RePlug | 0.3582 | Not recorded | 6979984ea2b28e761d87cd2d | | 0-shot | 0.3566 | Not recorded | 6979984ea2b28e761d87cd2d | | k-shot | 0.3509 | Not recorded | 6979984ea2b28e761d87cd2d | | LFM2 1.2B | 0.335 | Not recorded | 69ba317b0636e5bf4afc071e | | UR-RAG | 0.3184 | Not recorded | 6979984ea2b28e761d87cd2d | | RePlug | 0.3111 | Not recorded | 6979984ea2b28e761d87cd2d | | LURE-RAG | 0.3059 | Not recorded | 6979984ea2b28e761d87cd2d | | LURE-RAG (w/o topics) | 0.2994 | Not recorded | 6979984ea2b28e761d87cd2d | | k-shot | 0.2834 | Not recorded | 6979984ea2b28e761d87cd2d | | 0-shot | 0.2779 | Not recorded | 6979984ea2b28e761d87cd2d | | MobileLLM-Flash 650M | 0.2449 | Not recorded | 69ba317b0636e5bf4afc071e | | Llama3.2 1B | 0.2381 | Not recorded | 69ba317b0636e5bf4afc071e | | 0-shot | 0.2258 | Not recorded | 6979984ea2b28e761d87cd2d | | LFM2 700M | 0.225 | Not recorded | 69ba317b0636e5bf4afc071e | | MobileLLM-Flash 350M | 0.1984 | Not recorded | 69ba317b0636e5bf4afc071e | | Gemma3 270M | 0.154 | Not recorded | 69ba317b0636e5bf4afc071e | | LFM2 350M | 0.1497 | Not recorded | 69ba317b0636e5bf4afc071e | | Qwen3 0.6B | 0.0241 | Not recorded | 69ba317b0636e5bf4afc071e | ### UR-RAG Accuracy: 0.4177. Result ID: 6998a95b5698665ec40c0f88. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM":"Qwen-14B","Rank-By":"Utility","Retrieval Model":"Contriever"}. This record does not assert independent reproduction. ### RePlug Accuracy: 0.401. Result ID: 6998a95b5698665ec40c0f85. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM":"Qwen-14B","Rank-By":"Utility","Retrieval Model":"Contriever"}. This record does not assert independent reproduction. ### LURE-RAG (w/o topics) Accuracy: 0.401. Result ID: 6998a95b5698665ec40c0f87. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM":"Qwen-14B","Rank-By":"Utility","Retrieval Model":"Contriever"}. This record does not assert independent reproduction. ### LURE-RAG Accuracy: 0.3994. Result ID: 6998a95b5698665ec40c0f86. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM":"Qwen-14B","Rank-By":"Utility","Retrieval Model":"Contriever"}. This record does not assert independent reproduction. ### Gemma3 1B Accuracy: 0.398. Result ID: 69ba4def47f34ce924a3a513. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameter Count":"1B","Evaluation Protocol":"5-shot"}. This record does not assert independent reproduction. ### k-shot Accuracy: 0.3966. Result ID: 6998a95b5698665ec40c0f84. [Reporting paper]() Recorded evaluation configuration: {"LLM":"Qwen-14B","Rank-By":"Relevance","Retrieval Model":"Contriever"}. This record does not assert independent reproduction. ### UR-RAG Accuracy: 0.3699. Result ID: 6998a95b5698665ec40c0f82. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM":"phi-3.8B","Rank-By":"Utility","Retrieval Model":"Contriever"}. This record does not assert independent reproduction. ### LURE-RAG Accuracy: 0.3635. Result ID: 6998a95b5698665ec40c0f80. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM":"phi-3.8B","Rank-By":"Utility","Retrieval Model":"Contriever"}. This record does not assert independent reproduction. ### LURE-RAG (w/o topics) Accuracy: 0.3628. Result ID: 6998a95b5698665ec40c0f81. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM":"phi-3.8B","Rank-By":"Utility","Retrieval Model":"Contriever"}. This record does not assert independent reproduction. ### MobileLLM-Flash 1.4B Accuracy: 0.3606. Result ID: 69ba4def47f34ce924a3a516. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameter Count":"1.4B","Evaluation Protocol":"5-shot"}. This record does not assert independent reproduction. ### RePlug Accuracy: 0.3582. Result ID: 6998a95b5698665ec40c0f7f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM":"phi-3.8B","Rank-By":"Utility","Retrieval Model":"Contriever"}. This record does not assert independent reproduction. ### 0-shot Accuracy: 0.3566. Result ID: 6998a95b5698665ec40c0f83. [Reporting paper]() Recorded evaluation configuration: {"LLM":"Qwen-14B","Rank-By":"Relevance","Retrieval Model":"Contriever"}. This record does not assert independent reproduction. ### k-shot Accuracy: 0.3509. Result ID: 6998a95b5698665ec40c0f7e. [Reporting paper]() Recorded evaluation configuration: {"LLM":"phi-3.8B","Rank-By":"Relevance","Retrieval Model":"Contriever"}. This record does not assert independent reproduction. ### LFM2 1.2B Accuracy: 0.335. Result ID: 69ba4def47f34ce924a3a515. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameter Count":"1.2B","Evaluation Protocol":"5-shot"}. This record does not assert independent reproduction. ### UR-RAG Accuracy: 0.3184. Result ID: 6998a95b5698665ec40c0f7c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM":"llama-1B","Rank-By":"Utility","Retrieval Model":"Contriever"}. This record does not assert independent reproduction. ### RePlug Accuracy: 0.3111. Result ID: 6998a95b5698665ec40c0f79. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM":"llama-1B","Rank-By":"Utility","Retrieval Model":"Contriever"}. This record does not assert independent reproduction. ### LURE-RAG Accuracy: 0.3059. Result ID: 6998a95b5698665ec40c0f7a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM":"llama-1B","Rank-By":"Utility","Retrieval Model":"Contriever"}. This record does not assert independent reproduction. ### LURE-RAG (w/o topics) Accuracy: 0.2994. Result ID: 6998a95b5698665ec40c0f7b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM":"llama-1B","Rank-By":"Utility","Retrieval Model":"Contriever"}. This record does not assert independent reproduction. ### k-shot Accuracy: 0.2834. Result ID: 6998a95b5698665ec40c0f78. [Reporting paper]() Recorded evaluation configuration: {"LLM":"llama-1B","Rank-By":"Relevance","Retrieval Model":"Contriever"}. This record does not assert independent reproduction. ### 0-shot Accuracy: 0.2779. Result ID: 6998a95b5698665ec40c0f7d. [Reporting paper]() Recorded evaluation configuration: {"LLM":"phi-3.8B","Rank-By":"Relevance","Retrieval Model":"Contriever"}. This record does not assert independent reproduction. ### MobileLLM-Flash 650M Accuracy: 0.2449. Result ID: 69ba4def47f34ce924a3a512. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameter Count":"650M","Evaluation Protocol":"5-shot"}. This record does not assert independent reproduction. ### Llama3.2 1B Accuracy: 0.2381. Result ID: 69ba4def47f34ce924a3a514. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameter Count":"1B","Evaluation Protocol":"5-shot"}. This record does not assert independent reproduction. ### 0-shot Accuracy: 0.2258. Result ID: 6998a95b5698665ec40c0f77. [Reporting paper]() Recorded evaluation configuration: {"LLM":"llama-1B","Rank-By":"Relevance","Retrieval Model":"Contriever"}. This record does not assert independent reproduction. ### LFM2 700M Accuracy: 0.225. Result ID: 69ba4def47f34ce924a3a511. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameter Count":"700M","Evaluation Protocol":"5-shot"}. This record does not assert independent reproduction. ### MobileLLM-Flash 350M Accuracy: 0.1984. Result ID: 69ba4def47f34ce924a3a50f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameter Count":"350M","Evaluation Protocol":"5-shot"}. This record does not assert independent reproduction. ### Gemma3 270M Accuracy: 0.154. Result ID: 69ba4def47f34ce924a3a50d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameter Count":"270M","Evaluation Protocol":"5-shot"}. This record does not assert independent reproduction. ### LFM2 350M Accuracy: 0.1497. Result ID: 69ba4def47f34ce924a3a50e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameter Count":"350M","Evaluation Protocol":"5-shot"}. This record does not assert independent reproduction. ### Qwen3 0.6B Accuracy: 0.0241. Result ID: 69ba4def47f34ce924a3a510. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameter Count":"0.6B","Evaluation Protocol":"5-shot"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.