# Question Answering on TriviaQA (test) (Acc and F1) Source: [Question Answering on TriviaQA (test) (Acc and F1)]() Collection index: [llms.txt]() Data updated: 2026-03-25T13:31:22.724Z Evaluation of model performance on the test split of the TriviaQA dataset for Question Answering, 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 | Question Answering | | Dataset (including any stated split) | TriviaQA (test) | | Metric | F1 Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 27 of 27 | | 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. - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | F1 Score | Result date | Report paper | | --- | --- | --- | --- | | IGPO | 80.6 | Not recorded | 68fa7c2a1e209131cea8cccc | | DeepResearcher | 78.4 | Not recorded | 68fa7c2a1e209131cea8cccc | | R1-searcher | 73.1 | Not recorded | 68fa7c2a1e209131cea8cccc | | Search-r1-base | 71.9 | Not recorded | 68fa7c2a1e209131cea8cccc | | CoT+RAG | 68.9 | Not recorded | 68fa7c2a1e209131cea8cccc | | GiGPO | 64.7 | Not recorded | 68fa7c2a1e209131cea8cccc | | Search-o1 | 58.9 | Not recorded | 68fa7c2a1e209131cea8cccc | | CoT | 45.6 | Not recorded | 68fa7c2a1e209131cea8cccc | | Search-r1-instruct | 44.7 | Not recorded | 68fa7c2a1e209131cea8cccc | | UR-RAG | 42.39 | Not recorded | 6979984ea2b28e761d87cd2d | | RePlug | 41.25 | Not recorded | 6979984ea2b28e761d87cd2d | | LURE-RAG | 40.47 | Not recorded | 6979984ea2b28e761d87cd2d | | LURE-RAG (w/o topics) | 40.01 | Not recorded | 6979984ea2b28e761d87cd2d | | k-shot | 39.78 | Not recorded | 6979984ea2b28e761d87cd2d | | 0-shot | 35.87 | Not recorded | 6979984ea2b28e761d87cd2d | | UR-RAG | 34.72 | Not recorded | 6979984ea2b28e761d87cd2d | | RePlug | 33.21 | Not recorded | 6979984ea2b28e761d87cd2d | | LURE-RAG | 32.72 | Not recorded | 6979984ea2b28e761d87cd2d | | LURE-RAG (w/o topics) | 32.61 | Not recorded | 6979984ea2b28e761d87cd2d | | k-shot | 31.77 | Not recorded | 6979984ea2b28e761d87cd2d | | UR-RAG | 31.04 | Not recorded | 6979984ea2b28e761d87cd2d | | RePlug | 30.17 | Not recorded | 6979984ea2b28e761d87cd2d | | LURE-RAG | 30.1 | Not recorded | 6979984ea2b28e761d87cd2d | | LURE-RAG (w/o topics) | 29.73 | Not recorded | 6979984ea2b28e761d87cd2d | | k-shot | 26 | Not recorded | 6979984ea2b28e761d87cd2d | | 0-shot | 22.14 | Not recorded | 6979984ea2b28e761d87cd2d | | 0-shot | 21.37 | Not recorded | 6979984ea2b28e761d87cd2d | ### IGPO F1 Score: 80.6. Result ID: 69c3e3a847f34ce924ad6b82. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method Category":"Step-reward RL-based"}. This record does not assert independent reproduction. ### DeepResearcher F1 Score: 78.4. Result ID: 69c3e3a847f34ce924ad6b80. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method Category":"Outcome-reward RL-based"}. This record does not assert independent reproduction. ### R1-searcher F1 Score: 73.1. Result ID: 69c3e3a847f34ce924ad6b7f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method Category":"Outcome-reward RL-based"}. This record does not assert independent reproduction. ### Search-r1-base F1 Score: 71.9. Result ID: 69c3e3a847f34ce924ad6b7d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method Category":"Outcome-reward RL-based"}. This record does not assert independent reproduction. ### CoT+RAG F1 Score: 68.9. Result ID: 69c3e3a847f34ce924ad6b7b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method Category":"Prompt-based"}. This record does not assert independent reproduction. ### GiGPO F1 Score: 64.7. Result ID: 69c3e3a847f34ce924ad6b81. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method Category":"Step-reward RL-based"}. This record does not assert independent reproduction. ### Search-o1 F1 Score: 58.9. Result ID: 69c3e3a847f34ce924ad6b7c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Method Category":"Prompt-based"}. This record does not assert independent reproduction. ### CoT F1 Score: 45.6. Result ID: 69c3e3a847f34ce924ad6b7a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method Category":"Prompt-based"}. This record does not assert independent reproduction. ### Search-r1-instruct F1 Score: 44.7. Result ID: 69c3e3a847f34ce924ad6b7e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method Category":"Outcome-reward RL-based"}. This record does not assert independent reproduction. ### UR-RAG F1 Score: 42.39. Result ID: 6998a95b5698665ec40c0fac. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Rank-By":"Utility","LLM Backbone":"Qwen-14B","Retrieval Method":"BM25"}. This record does not assert independent reproduction. ### RePlug F1 Score: 41.25. Result ID: 6998a95b5698665ec40c0fa9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Rank-By":"Utility","LLM Backbone":"Qwen-14B","Retrieval Method":"BM25"}. This record does not assert independent reproduction. ### LURE-RAG F1 Score: 40.47. Result ID: 6998a95b5698665ec40c0faa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Rank-By":"Utility","LLM Backbone":"Qwen-14B","Retrieval Method":"BM25"}. This record does not assert independent reproduction. ### LURE-RAG (w/o topics) F1 Score: 40.01. Result ID: 6998a95b5698665ec40c0fab. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Rank-By":"Utility","LLM Backbone":"Qwen-14B","Retrieval Method":"BM25"}. This record does not assert independent reproduction. ### k-shot F1 Score: 39.78. Result ID: 6998a95b5698665ec40c0fa8. [Reporting paper]() Recorded evaluation configuration: {"Rank-By":"Relevance","LLM Backbone":"Qwen-14B","Retrieval Method":"BM25"}. This record does not assert independent reproduction. ### 0-shot F1 Score: 35.87. Result ID: 6998a95b5698665ec40c0fa7. [Reporting paper]() Recorded evaluation configuration: {"Rank-By":"Relevance","LLM Backbone":"Qwen-14B","Retrieval Method":"BM25"}. This record does not assert independent reproduction. ### UR-RAG F1 Score: 34.72. Result ID: 6998a95b5698665ec40c0fa6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Rank-By":"Utility","LLM Backbone":"phi-3.8B","Retrieval Method":"BM25"}. This record does not assert independent reproduction. ### RePlug F1 Score: 33.21. Result ID: 6998a95b5698665ec40c0fa3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Rank-By":"Utility","LLM Backbone":"phi-3.8B","Retrieval Method":"BM25"}. This record does not assert independent reproduction. ### LURE-RAG F1 Score: 32.72. Result ID: 6998a95b5698665ec40c0fa4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Rank-By":"Utility","LLM Backbone":"phi-3.8B","Retrieval Method":"BM25"}. This record does not assert independent reproduction. ### LURE-RAG (w/o topics) F1 Score: 32.61. Result ID: 6998a95b5698665ec40c0fa5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Rank-By":"Utility","LLM Backbone":"phi-3.8B","Retrieval Method":"BM25"}. This record does not assert independent reproduction. ### k-shot F1 Score: 31.77. Result ID: 6998a95b5698665ec40c0fa2. [Reporting paper]() Recorded evaluation configuration: {"Rank-By":"Relevance","LLM Backbone":"phi-3.8B","Retrieval Method":"BM25"}. This record does not assert independent reproduction. ### UR-RAG F1 Score: 31.04. Result ID: 6998a95b5698665ec40c0fa0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Rank-By":"Utility","LLM Backbone":"llama-1B","Retrieval Method":"BM25"}. This record does not assert independent reproduction. ### RePlug F1 Score: 30.17. Result ID: 6998a95b5698665ec40c0f9d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Rank-By":"Utility","LLM Backbone":"llama-1B","Retrieval Method":"BM25"}. This record does not assert independent reproduction. ### LURE-RAG F1 Score: 30.1. Result ID: 6998a95b5698665ec40c0f9e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Rank-By":"Utility","LLM Backbone":"llama-1B","Retrieval Method":"BM25"}. This record does not assert independent reproduction. ### LURE-RAG (w/o topics) F1 Score: 29.73. Result ID: 6998a95b5698665ec40c0f9f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Rank-By":"Utility","LLM Backbone":"llama-1B","Retrieval Method":"BM25"}. This record does not assert independent reproduction. ### k-shot F1 Score: 26. Result ID: 6998a95b5698665ec40c0f9c. [Reporting paper]() Recorded evaluation configuration: {"Rank-By":"Relevance","LLM Backbone":"llama-1B","Retrieval Method":"BM25"}. This record does not assert independent reproduction. ### 0-shot F1 Score: 22.14. Result ID: 6998a95b5698665ec40c0fa1. [Reporting paper]() Recorded evaluation configuration: {"Rank-By":"Relevance","LLM Backbone":"phi-3.8B","Retrieval Method":"BM25"}. This record does not assert independent reproduction. ### 0-shot F1 Score: 21.37. Result ID: 6998a95b5698665ec40c0f9b. [Reporting paper]() Recorded evaluation configuration: {"Rank-By":"Relevance","LLM Backbone":"llama-1B","Retrieval Method":"BM25"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.