# Question Answering (Truthfulness) on TruthfulQA (Accuracy) Source: [Question Answering (Truthfulness) on TruthfulQA (Accuracy)]() Collection index: [llms.txt]() Data updated: 2026-05-19T10:02:07.618Z Evaluation of model performance on the TruthfulQA dataset, reporting only the Accuracy 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 | Question Answering (Truthfulness) | | Dataset (including any stated split) | TruthfulQA | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 12 of 12 | | 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 | | --- | --- | --- | --- | | AgentRevive | 72.05 | Not recorded | 6a0bee9bdbc836b87d82c465 | | AgentDropout | 69.11 | Not recorded | 6a0bee9bdbc836b87d82c465 | | ARG-Designer | 68.02 | Not recorded | 6a0bee9bdbc836b87d82c465 | | G-Designer | 67.55 | Not recorded | 6a0bee9bdbc836b87d82c465 | | AgentPrune | 67.41 | Not recorded | 6a0bee9bdbc836b87d82c465 | | AgentVerse | 66.64 | Not recorded | 6a0bee9bdbc836b87d82c465 | | Autogen | 65.89 | Not recorded | 6a0bee9bdbc836b87d82c465 | | MASround=T | 65.76 | Not recorded | 6a0bee9bdbc836b87d82c465 | | SC (CoT) | 64.85 | Not recorded | 6a0bee9bdbc836b87d82c465 | | CoT | 64.61 | Not recorded | 6a0bee9bdbc836b87d82c465 | | MASround=1 | 63.98 | Not recorded | 6a0bee9bdbc836b87d82c465 | | Vanilla | 62.98 | Not recorded | 6a0bee9bdbc836b87d82c465 | ### AgentRevive Accuracy: 72.05. Result ID: 6a0c34b7fbc373592c02ce3d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Var. NS":"True","Flex. State":"True","Base model":"Qwen2.5-72B-Instruct"}. This record does not assert independent reproduction. ### AgentDropout Accuracy: 69.11. Result ID: 6a0c34b7fbc373592c02ce3c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Var. NS":"True","Flex. State":"False","Base model":"Qwen2.5-72B-Instruct"}. This record does not assert independent reproduction. ### ARG-Designer Accuracy: 68.02. Result ID: 6a0c34b7fbc373592c02ce3b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Var. NS":"True","Flex. State":"False","Base model":"Qwen2.5-72B-Instruct"}. This record does not assert independent reproduction. ### G-Designer Accuracy: 67.55. Result ID: 6a0c34b7fbc373592c02ce39. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Var. NS":"False","Flex. State":"False","Base model":"Qwen2.5-72B-Instruct"}. This record does not assert independent reproduction. ### AgentPrune Accuracy: 67.41. Result ID: 6a0c34b7fbc373592c02ce3a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Var. NS":"False","Flex. State":"False","Base model":"Qwen2.5-72B-Instruct"}. This record does not assert independent reproduction. ### AgentVerse Accuracy: 66.64. Result ID: 6a0c34b7fbc373592c02ce36. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Var. NS":"False","Flex. State":"False","Base model":"Qwen2.5-72B-Instruct"}. This record does not assert independent reproduction. ### Autogen Accuracy: 65.89. Result ID: 6a0c34b7fbc373592c02ce35. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Var. NS":"False","Flex. State":"False","Base model":"Qwen2.5-72B-Instruct"}. This record does not assert independent reproduction. ### MASround=T Accuracy: 65.76. Result ID: 6a0c34b7fbc373592c02ce38. [Reporting paper]() Recorded evaluation configuration: {"Var. NS":"False","Flex. State":"False","Base model":"Qwen2.5-72B-Instruct"}. This record does not assert independent reproduction. ### SC (CoT) Accuracy: 64.85. Result ID: 6a0c34b7fbc373592c02ce34. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Var. NS":"False","Flex. State":"False","Base model":"Qwen2.5-72B-Instruct"}. This record does not assert independent reproduction. ### CoT Accuracy: 64.61. Result ID: 6a0c34b7fbc373592c02ce33. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Var. NS":"False","Flex. State":"False","Base model":"Qwen2.5-72B-Instruct"}. This record does not assert independent reproduction. ### MASround=1 Accuracy: 63.98. Result ID: 6a0c34b7fbc373592c02ce37. [Reporting paper]() Recorded evaluation configuration: {"Var. NS":"False","Flex. State":"False","Base model":"Qwen2.5-72B-Instruct"}. This record does not assert independent reproduction. ### Vanilla Accuracy: 62.98. Result ID: 6a0c34b7fbc373592c02ce32. [Reporting paper]() Recorded evaluation configuration: {"Var. NS":"False","Flex. State":"False","Base model":"Qwen2.5-72B-Instruct"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.