# Open-domain Question Answering on Natural Questions (Metric) Source: [Open-domain Question Answering on Natural Questions (Metric)]() Collection index: [llms.txt]() Data updated: 2026-02-27T07:30:43.133Z Evaluation of model performance on the Natural Questions dataset for Open-domain Question Answering, measured using the metric labeled 'Metric'. 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) | Natural Questions | | Metric | QA Metric Score | | Unit | SCALAR | | 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 - [QA Metric Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | QA Metric Score | Result date | Report paper | | --- | --- | --- | --- | | PaLM | 39.6 | Not recorded | 68fa6d931e209131cea3abf2 | | Chinchilla | 31.5 | Not recorded | 68fa6d931e209131cea3abf2 | | PaLM | 27.6 | Not recorded | 68fa6d931e209131cea3abf2 | | Gopher | 24.5 | Not recorded | 68fa6d931e209131cea3abf2 | | PaLM | 21.2 | Not recorded | 68fa6d931e209131cea3abf2 | | PaLM | 18.1 | Not recorded | 68fa6d931e209131cea3abf2 | | Chinchilla | 16.6 | Not recorded | 68fa6d931e209131cea3abf2 | | PaLM | 14.6 | Not recorded | 68fa6d931e209131cea3abf2 | | Gopher | 10.1 | Not recorded | 68fa6d931e209131cea3abf2 | | PaLM | 8.4 | Not recorded | 68fa6d931e209131cea3abf2 | ### PaLM QA Metric Score: 39.6. Result ID: 69a1481c35dfcabb00e5fcd3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size (Billions of Parameters)":"540","Num Tokens (Billions of Tokens)":"780","Training FLOP Count (Zettaflops)":"2527.2","Evaluation Protocol":"few-shot"}. This record does not assert independent reproduction. ### Chinchilla QA Metric Score: 31.5. Result ID: 69a1481c35dfcabb00e5fcd4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size (Billions of Parameters)":"70","Num Tokens (Billions of Tokens)":"1400","Training FLOP Count (Zettaflops)":"588.0","Evaluation Protocol":"few-shot"}. This record does not assert independent reproduction. ### PaLM QA Metric Score: 27.6. Result ID: 69a1481c35dfcabb00e5fcd2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size (Billions of Parameters)":"62","Num Tokens (Billions of Tokens)":"795","Training FLOP Count (Zettaflops)":"295.7","Evaluation Protocol":"few-shot"}. This record does not assert independent reproduction. ### Gopher QA Metric Score: 24.5. Result ID: 69a1481c35dfcabb00e5fcd5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size (Billions of Parameters)":"280","Num Tokens (Billions of Tokens)":"300","Training FLOP Count (Zettaflops)":"504.0","Evaluation Protocol":"few-shot"}. This record does not assert independent reproduction. ### PaLM QA Metric Score: 21.2. Result ID: 69a1481c35dfcabb00e5fcce. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size (Billions of Parameters)":"540","Num Tokens (Billions of Tokens)":"780","Training FLOP Count (Zettaflops)":"2527.2","Evaluation Protocol":"0-shot"}. This record does not assert independent reproduction. ### PaLM QA Metric Score: 18.1. Result ID: 69a1481c35dfcabb00e5fccd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size (Billions of Parameters)":"62","Num Tokens (Billions of Tokens)":"795","Training FLOP Count (Zettaflops)":"295.7","Evaluation Protocol":"0-shot"}. This record does not assert independent reproduction. ### Chinchilla QA Metric Score: 16.6. Result ID: 69a1481c35dfcabb00e5fccf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size (Billions of Parameters)":"70","Num Tokens (Billions of Tokens)":"1400","Training FLOP Count (Zettaflops)":"588.0","Evaluation Protocol":"0-shot"}. This record does not assert independent reproduction. ### PaLM QA Metric Score: 14.6. Result ID: 69a1481c35dfcabb00e5fcd1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size (Billions of Parameters)":"8","Num Tokens (Billions of Tokens)":"780","Training FLOP Count (Zettaflops)":"37.4","Evaluation Protocol":"few-shot"}. This record does not assert independent reproduction. ### Gopher QA Metric Score: 10.1. Result ID: 69a1481c35dfcabb00e5fcd0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size (Billions of Parameters)":"280","Num Tokens (Billions of Tokens)":"300","Training FLOP Count (Zettaflops)":"504.0","Evaluation Protocol":"0-shot"}. This record does not assert independent reproduction. ### PaLM QA Metric Score: 8.4. Result ID: 69a1481c35dfcabb00e5fccc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size (Billions of Parameters)":"8","Num Tokens (Billions of Tokens)":"780","Training FLOP Count (Zettaflops)":"37.4","Evaluation Protocol":"0-shot"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.