# Open-domain Question Answering on TriviaQA (Acc. %, AUROC, ECE) Source: [Open-domain Question Answering on TriviaQA (Acc. %, AUROC, ECE)]() Collection index: [llms.txt]() Data updated: 2026-05-29T10:11:14.842Z Evaluation of Open-domain Question Answering performance on the TriviaQA dataset, reporting Accuracy (%), AUROC, and Expected Calibration Error (ECE). 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 | | Metric | Accuracy (%) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 17 of 17 | | 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. - [AUROC](): Higher is better; unit: SCALAR. - [Expected Calibration Error (%)](): Lower is better; unit: PERCENT. - [Score (SC)](): Higher is better; unit: SCALAR. ## Recorded results | Method | Accuracy (%) | Result date | Report paper | | --- | --- | --- | --- | | HiPRAG | 74 | Not recorded | 6a191dd5dbd7150506f82adc | | SAAS | 74 | Not recorded | 6a191dd5dbd7150506f82adc | | Qwen3 30B | 72.99 | Not recorded | 69afa57c2d603e6de3e439a8 | | Gemma3 12B | 72.04 | Not recorded | 69afa57c2d603e6de3e439a8 | | SAAS | 69.2 | Not recorded | 6a191dd5dbd7150506f82adc | | HiPRAG | 68.8 | Not recorded | 6a191dd5dbd7150506f82adc | | Search-R1 | 68.3 | Not recorded | 6a191dd5dbd7150506f82adc | | StepSearch | 67.8 | Not recorded | 6a191dd5dbd7150506f82adc | | RFT | 67.5 | Not recorded | 6a191dd5dbd7150506f82adc | | Search-R1 | 65.7 | Not recorded | 6a191dd5dbd7150506f82adc | | GLM4 9B | 60.52 | Not recorded | 69afa57c2d603e6de3e439a8 | | StepSearch | 60 | Not recorded | 6a191dd5dbd7150506f82adc | | RFT | 59.8 | Not recorded | 6a191dd5dbd7150506f82adc | | Direct Inference | 55.7 | Not recorded | 6a191dd5dbd7150506f82adc | | Qwen3 4B | 54.21 | Not recorded | 69afa57c2d603e6de3e439a8 | | Gemma3 4B | 53.36 | Not recorded | 69afa57c2d603e6de3e439a8 | | Direct Inference | 44.9 | Not recorded | 6a191dd5dbd7150506f82adc | ### HiPRAG Accuracy (%): 74. Result ID: 6a196626fbc373592c1449c0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### SAAS Accuracy (%): 74. Result ID: 6a196626fbc373592c1449c1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### Qwen3 30B Accuracy (%): 72.99. Result ID: 69afcba26dbb7075b957da17. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"confidence\_type":"normalized","evaluation\_protocol":"self-evaluation"}. This record does not assert independent reproduction. ### Gemma3 12B Accuracy (%): 72.04. Result ID: 69afcba26dbb7075b957da19. [Reporting paper]() Recorded evaluation configuration: {"confidence\_type":"normalized","evaluation\_protocol":"self-evaluation"}. This record does not assert independent reproduction. ### SAAS Accuracy (%): 69.2. Result ID: 6a196626fbc373592c1449bb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-3B-Instruct"}. This record does not assert independent reproduction. ### HiPRAG Accuracy (%): 68.8. Result ID: 6a196626fbc373592c1449ba. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-3B-Instruct"}. This record does not assert independent reproduction. ### Search-R1 Accuracy (%): 68.3. Result ID: 6a196626fbc373592c1449be. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### StepSearch Accuracy (%): 67.8. Result ID: 6a196626fbc373592c1449bf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### RFT Accuracy (%): 67.5. Result ID: 6a196626fbc373592c1449bd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### Search-R1 Accuracy (%): 65.7. Result ID: 6a196626fbc373592c1449b8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-3B-Instruct"}. This record does not assert independent reproduction. ### GLM4 9B Accuracy (%): 60.52. Result ID: 69afcba26dbb7075b957da1a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"confidence\_type":"normalized","evaluation\_protocol":"self-evaluation"}. This record does not assert independent reproduction. ### StepSearch Accuracy (%): 60. Result ID: 6a196626fbc373592c1449b9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-3B-Instruct"}. This record does not assert independent reproduction. ### RFT Accuracy (%): 59.8. Result ID: 6a196626fbc373592c1449b7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-3B-Instruct"}. This record does not assert independent reproduction. ### Direct Inference Accuracy (%): 55.7. Result ID: 6a196626fbc373592c1449bc. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### Qwen3 4B Accuracy (%): 54.21. Result ID: 69afcba26dbb7075b957da16. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"confidence\_type":"normalized","evaluation\_protocol":"self-evaluation"}. This record does not assert independent reproduction. ### Gemma3 4B Accuracy (%): 53.36. Result ID: 69afcba26dbb7075b957da18. [Reporting paper]() Recorded evaluation configuration: {"confidence\_type":"normalized","evaluation\_protocol":"self-evaluation"}. This record does not assert independent reproduction. ### Direct Inference Accuracy (%): 44.9. Result ID: 6a196626fbc373592c1449b6. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-3B-Instruct"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.