# Evidence Grounding on SQuAD v1.1 (test) Source: [Evidence Grounding on SQuAD v1.1 (test)]() Collection index: [llms.txt]() Data updated: 2026-03-18T08:31:53.511Z Evaluation of model performance on the test split of the SQuAD v1.1 dataset for the Evidence Grounding task, reporting metrics such as F1, WER, and Hit-Rate. 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 | Evidence Grounding | | Dataset (including any stated split) | SQuAD v1.1 (test) | | Metric | F1 Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 10 of 10 | | 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. - [WER](): Lower is better; unit: SCALAR. - [Hit Rate](): Higher is better; unit: PERCENT. - [Latency](): Lower is better; unit: TIME. ## Recorded results | Method | F1 Score | Result date | Report paper | | --- | --- | --- | --- | | AEG (with LFE) | 80.02 | Not recorded | 69ba31830636e5bf4afc075c | | Whisper-Large-v3 + Qwen3-Reranker-8B | 79.14 | Not recorded | 69ba31830636e5bf4afc075c | | Whisper-Medium + Qwen3-Reranker-8B | 78.91 | Not recorded | 69ba31830636e5bf4afc075c | | Whisper-Small + Qwen3-Reranker-8B | 78.29 | Not recorded | 69ba31830636e5bf4afc075c | | Whisper-Large-v3 + bge-reranker-v2-m3 | 74.56 | Not recorded | 69ba31830636e5bf4afc075c | | Whisper-Large-v3 + Qwen3-Reranker-4B | 74.25 | Not recorded | 69ba31830636e5bf4afc075c | | Whisper-Medium + bge-reranker-v2-m3 | 74.17 | Not recorded | 69ba31830636e5bf4afc075c | | Whisper-Medium + Qwen3-Reranker-4B | 73.88 | Not recorded | 69ba31830636e5bf4afc075c | | Whisper-Small + bge-reranker-v2-m3 | 73.85 | Not recorded | 69ba31830636e5bf4afc075c | | Whisper-Small + Qwen3-Reranker-4B | 73.56 | Not recorded | 69ba31830636e5bf4afc075c | ### AEG (with LFE) F1 Score: 80.02. Result ID: 69ba62a047f34ce924a44533. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Configuration":"AEG (with LFE)","Params":"8.2B"}. This record does not assert independent reproduction. ### Whisper-Large-v3 + Qwen3-Reranker-8B F1 Score: 79.14. Result ID: 69ba62a047f34ce924a44532. [Reporting paper]() Recorded evaluation configuration: {"Configuration":"Whisper-Large-v3 + Qwen3-Reranker-8B","Params":"9.6B"}. This record does not assert independent reproduction. ### Whisper-Medium + Qwen3-Reranker-8B F1 Score: 78.91. Result ID: 69ba62a047f34ce924a44531. [Reporting paper]() Recorded evaluation configuration: {"Configuration":"Whisper-Medium + Qwen3-Reranker-8B","Params":"8.8B"}. This record does not assert independent reproduction. ### Whisper-Small + Qwen3-Reranker-8B F1 Score: 78.29. Result ID: 69ba62a047f34ce924a44530. [Reporting paper]() Recorded evaluation configuration: {"Configuration":"Whisper-Small + Qwen3-Reranker-8B","Params":"8.2B"}. This record does not assert independent reproduction. ### Whisper-Large-v3 + bge-reranker-v2-m3 F1 Score: 74.56. Result ID: 69ba62a047f34ce924a4452c. [Reporting paper]() Recorded evaluation configuration: {"Configuration":"Whisper-Large-v3 + bge-reranker-v2-m3","Params":"2.1B"}. This record does not assert independent reproduction. ### Whisper-Large-v3 + Qwen3-Reranker-4B F1 Score: 74.25. Result ID: 69ba62a047f34ce924a4452f. [Reporting paper]() Recorded evaluation configuration: {"Configuration":"Whisper-Large-v3 + Qwen3-Reranker-4B","Params":"5.6B"}. This record does not assert independent reproduction. ### Whisper-Medium + bge-reranker-v2-m3 F1 Score: 74.17. Result ID: 69ba62a047f34ce924a4452b. [Reporting paper]() Recorded evaluation configuration: {"Configuration":"Whisper-Medium + bge-reranker-v2-m3","Params":"1.3B"}. This record does not assert independent reproduction. ### Whisper-Medium + Qwen3-Reranker-4B F1 Score: 73.88. Result ID: 69ba62a047f34ce924a4452e. [Reporting paper]() Recorded evaluation configuration: {"Configuration":"Whisper-Medium + Qwen3-Reranker-4B","Params":"4.8B"}. This record does not assert independent reproduction. ### Whisper-Small + bge-reranker-v2-m3 F1 Score: 73.85. Result ID: 69ba62a047f34ce924a4452a. [Reporting paper]() Recorded evaluation configuration: {"Configuration":"Whisper-Small + bge-reranker-v2-m3","Params":"0.8B"}. This record does not assert independent reproduction. ### Whisper-Small + Qwen3-Reranker-4B F1 Score: 73.56. Result ID: 69ba62a047f34ce924a4452d. [Reporting paper]() Recorded evaluation configuration: {"Configuration":"Whisper-Small + Qwen3-Reranker-4B","Params":"4.2B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.