# Question Answering on TruthfulQA matched-N (test) Source: [Question Answering on TruthfulQA matched-N (test)]() Collection index: [llms.txt]() Data updated: 2026-06-01T08:04:24.912Z Evaluation of model performance on the matched-N subset of the TruthfulQA test set, reporting Accuracy. 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 | Question Answering | | Dataset (including any stated split) | TruthfulQA matched-N (test) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 11 of 11 | | 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. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Oracle topology | 31.67 | Not recorded | 6a1d120fdbd7150506f83faf | | CAGE-SELECT | 24 | Not recorded | 6a1d120fdbd7150506f83faf | | debate | 23.67 | Not recorded | 6a1d120fdbd7150506f83faf | | Per-bench best fixed | 23.67 | Not recorded | 6a1d120fdbd7150506f83faf | | Highest plurality share | 22.33 | Not recorded | 6a1d120fdbd7150506f83faf | | Highest mean log-prob | 22.33 | Not recorded | 6a1d120fdbd7150506f83faf | | chain | 20.67 | Not recorded | 6a1d120fdbd7150506f83faf | | hub-spoke | 20.33 | Not recorded | 6a1d120fdbd7150506f83faf | | iid | 20 | Not recorded | 6a1d120fdbd7150506f83faf | | tree | 19.67 | Not recorded | 6a1d120fdbd7150506f83faf | | Majority over topologies | 19 | Not recorded | 6a1d120fdbd7150506f83faf | ### Oracle topology Accuracy: 31.67. Result ID: 6a1d3b79fbc373592c1636e4. [Reporting paper]() Recorded evaluation configuration: {"Topology Category":"Confidence-routed"}. This record does not assert independent reproduction. ### CAGE-SELECT Accuracy: 24. Result ID: 6a1d3b79fbc373592c1636e3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Topology Category":"Confidence-routed"}. This record does not assert independent reproduction. ### debate Accuracy: 23.67. Result ID: 6a1d3b79fbc373592c1636db. [Reporting paper]() Recorded evaluation configuration: {"Topology Category":"Fixed topology"}. This record does not assert independent reproduction. ### Per-bench best fixed Accuracy: 23.67. Result ID: 6a1d3b79fbc373592c1636df. [Reporting paper]() Recorded evaluation configuration: {"Topology Category":"Fixed topology"}. This record does not assert independent reproduction. ### Highest plurality share Accuracy: 22.33. Result ID: 6a1d3b79fbc373592c1636e1. [Reporting paper]() Recorded evaluation configuration: {"Topology Category":"Selection w/o learned confidence"}. This record does not assert independent reproduction. ### Highest mean log-prob Accuracy: 22.33. Result ID: 6a1d3b79fbc373592c1636e2. [Reporting paper]() Recorded evaluation configuration: {"Topology Category":"Selection w/o learned confidence"}. This record does not assert independent reproduction. ### chain Accuracy: 20.67. Result ID: 6a1d3b79fbc373592c1636dc. [Reporting paper]() Recorded evaluation configuration: {"Topology Category":"Fixed topology"}. This record does not assert independent reproduction. ### hub-spoke Accuracy: 20.33. Result ID: 6a1d3b79fbc373592c1636dd. [Reporting paper]() Recorded evaluation configuration: {"Topology Category":"Fixed topology"}. This record does not assert independent reproduction. ### iid Accuracy: 20. Result ID: 6a1d3b79fbc373592c1636da. [Reporting paper]() Recorded evaluation configuration: {"Topology Category":"Fixed topology"}. This record does not assert independent reproduction. ### tree Accuracy: 19.67. Result ID: 6a1d3b79fbc373592c1636de. [Reporting paper]() Recorded evaluation configuration: {"Topology Category":"Fixed topology"}. This record does not assert independent reproduction. ### Majority over topologies Accuracy: 19. Result ID: 6a1d3b79fbc373592c1636e0. [Reporting paper]() Recorded evaluation configuration: {"Topology Category":"Selection w/o learned confidence"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.