# Long-form Question Answering on AlpacaFact Source: [Long-form Question Answering on AlpacaFact]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:08:13.719Z Evaluation of model performance on the AlpacaFact dataset for Long-form Question Answering, measured using VeriScore F1 and AlpacaEval Win 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 | Long-form Question Answering | | Dataset (including any stated split) | AlpacaFact | | Metric | VeriScore F1 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 14 of 14 | | 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 - [VeriScore F1](): Higher is better; unit: PERCENT. - [AlpacaEval Win Rate](): Higher is better; unit: PERCENT. ## Recorded results | Method | VeriScore F1 | Result date | Report paper | | --- | --- | --- | --- | | EWE | 66.9 | Not recorded | 68fa79081e209131cea7bc9f | | RA | 66 | Not recorded | 68fa79081e209131cea7bc9f | | EWE | 65.5 | Not recorded | 68fa79081e209131cea7bc9f | | DRAGIN | 65.3 | Not recorded | 68fa79081e209131cea7bc9f | | Llama-3.1 | 65.3 | Not recorded | 68fa79081e209131cea7bc9f | | COVE w/ Retrieval | 64 | Not recorded | 68fa79081e209131cea7bc9f | | RA | 63.9 | Not recorded | 68fa79081e209131cea7bc9f | | Llama-3.1 | 63.8 | Not recorded | 68fa79081e209131cea7bc9f | | COVE | 61.5 | Not recorded | 68fa79081e209131cea7bc9f | | DRAGIN | 61.3 | Not recorded | 68fa79081e209131cea7bc9f | | NEST | 58.1 | Not recorded | 68fa79081e209131cea7bc9f | | NEST | 57.8 | Not recorded | 68fa79081e209131cea7bc9f | | COVE w/ Retrieval | 54.6 | Not recorded | 68fa79081e209131cea7bc9f | | COVE | 51.3 | Not recorded | 68fa79081e209131cea7bc9f | ### EWE VeriScore F1: 66.9. Result ID: 6995bc933badfaffe6be5768. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Base Model":"Llama-3.1 70B"}. This record does not assert independent reproduction. ### RA VeriScore F1: 66. Result ID: 6995bc933badfaffe6be5763. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Base Model":"Llama-3.1 70B"}. This record does not assert independent reproduction. ### EWE VeriScore F1: 65.5. Result ID: 6995bc933badfaffe6be576f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Base Model":"Llama-3.1 8B"}. This record does not assert independent reproduction. ### DRAGIN VeriScore F1: 65.3. Result ID: 6995bc933badfaffe6be5765. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Llama-3.1 70B"}. This record does not assert independent reproduction. ### Llama-3.1 VeriScore F1: 65.3. Result ID: 6995bc933badfaffe6be5769. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Base Model":"Llama-3.1 8B"}. This record does not assert independent reproduction. ### COVE w/ Retrieval VeriScore F1: 64. Result ID: 6995bc933badfaffe6be5767. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Llama-3.1 70B"}. This record does not assert independent reproduction. ### RA VeriScore F1: 63.9. Result ID: 6995bc933badfaffe6be576a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Base Model":"Llama-3.1 8B"}. This record does not assert independent reproduction. ### Llama-3.1 VeriScore F1: 63.8. Result ID: 6995bc933badfaffe6be5762. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Base Model":"Llama-3.1 70B"}. This record does not assert independent reproduction. ### COVE VeriScore F1: 61.5. Result ID: 6995bc933badfaffe6be5766. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Llama-3.1 70B"}. This record does not assert independent reproduction. ### DRAGIN VeriScore F1: 61.3. Result ID: 6995bc933badfaffe6be576c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Llama-3.1 8B"}. This record does not assert independent reproduction. ### NEST VeriScore F1: 58.1. Result ID: 6995bc933badfaffe6be5764. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Llama-3.1 70B"}. This record does not assert independent reproduction. ### NEST VeriScore F1: 57.8. Result ID: 6995bc933badfaffe6be576b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Llama-3.1 8B"}. This record does not assert independent reproduction. ### COVE w/ Retrieval VeriScore F1: 54.6. Result ID: 6995bc933badfaffe6be576e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Llama-3.1 8B"}. This record does not assert independent reproduction. ### COVE VeriScore F1: 51.3. Result ID: 6995bc933badfaffe6be576d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Llama-3.1 8B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.