# Factoid Question Answering on BioASQ Task B Source: [Factoid Question Answering on BioASQ Task B]() Collection index: [llms.txt]() Data updated: 2026-04-14T10:41:30.903Z Evaluation of model performance on the BioASQ Task B dataset for Factoid Question Answering, reporting Strict, Lenient, and MRR metrics. 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 | Factoid Question Answering | | Dataset (including any stated split) | BioASQ Task B | | Metric | Strict Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 6 of 6 | | 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 - [Strict Score](): Higher is better; unit: PERCENT. - [Lenient Score](): Higher is better; unit: PERCENT. - [MRR](): Higher is better; unit: PERCENT. ## Recorded results | Method | Strict Score | Result date | Report paper | | --- | --- | --- | --- | | GPT4-Turbo | 55.05 | Not recorded | 68fa7c461e209131cea8d5a4 | | ParallaxRAG + Qwen3-Plus | 42.1 | Not recorded | 68fa7c461e209131cea8d5a4 | | Single-View + Qwen3-Plus | 37.73 | Not recorded | 68fa7c461e209131cea8d5a4 | | GPT-4o | 34.62 | Not recorded | 68fa7c461e209131cea8d5a4 | | Qwen3-Plus | 32.19 | Not recorded | 68fa7c461e209131cea8d5a4 | | Deepseek-R1-8B | 26.2 | Not recorded | 68fa7c461e209131cea8d5a4 | ### GPT4-Turbo Strict Score: 55.05. Result ID: 69de196047f34ce924c642f0. [Reporting paper]() Recorded evaluation configuration: {"Generator":"GPT4-Turbo","Retriever":"None"}. This record does not assert independent reproduction. ### ParallaxRAG + Qwen3-Plus Strict Score: 42.1. Result ID: 69de196047f34ce924c642f4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Generator":"Qwen3-Plus","Retriever":"ParallaxRAG"}. This record does not assert independent reproduction. ### Single-View + Qwen3-Plus Strict Score: 37.73. Result ID: 69de196047f34ce924c642f3. [Reporting paper]() Recorded evaluation configuration: {"Generator":"Qwen3-Plus","Retriever":"Single-View"}. This record does not assert independent reproduction. ### GPT-4o Strict Score: 34.62. Result ID: 69de196047f34ce924c642f1. [Reporting paper]() Recorded evaluation configuration: {"Generator":"GPT-4o","Retriever":"None"}. This record does not assert independent reproduction. ### Qwen3-Plus Strict Score: 32.19. Result ID: 69de196047f34ce924c642f2. [Reporting paper]() Recorded evaluation configuration: {"Generator":"Qwen3-Plus","Retriever":"None"}. This record does not assert independent reproduction. ### Deepseek-R1-8B Strict Score: 26.2. Result ID: 69de196047f34ce924c642ef. [Reporting paper]() Recorded evaluation configuration: {"Generator":"Deepseek-R1-8B","Retriever":"None"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.