# Hallucination Evaluation on HallusionBench 1.0 (test) Source: [Hallucination Evaluation on HallusionBench 1.0 (test)]() Collection index: [llms.txt]() Data updated: 2026-05-13T08:54:00.847Z Evaluation of model performance on hallucination detection using the test split (version 1.0) of the HallusionBench dataset, measured by specific accuracy metrics (fACC, qACC, easyA, hardA, aACC). 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 | Hallucination Evaluation | | Dataset (including any stated split) | HallusionBench 1.0 (test) | | Metric | fACC | | 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 - [fACC](): Higher is better; unit: PERCENT. - [qACC](): Higher is better; unit: PERCENT. - [easyA](): Higher is better; unit: PERCENT. - [hardA](): Higher is better; unit: PERCENT. - [aACC](): Higher is better; unit: PERCENT. ## Recorded results | Method | fACC | Result date | Report paper | | --- | --- | --- | --- | | LaSCD | 22.2 | Not recorded | 6a0405bfdbc836b87d827743 | | DeCo | 20.2 | Not recorded | 6a0405bfdbc836b87d827743 | | Qwen-VL | 19.9 | Not recorded | 6a0405bfdbc836b87d827743 | | LLaVA-1.5 | 17.9 | Not recorded | 6a0405bfdbc836b87d827743 | | MemVR | 17.9 | Not recorded | 6a0405bfdbc836b87d827743 | | OPERA | 16.2 | Not recorded | 6a0405bfdbc836b87d827743 | | LaSCD | 15.8 | Not recorded | 6a0405bfdbc836b87d827743 | | DeCo | 15.3 | Not recorded | 6a0405bfdbc836b87d827743 | | ICD | 13.9 | Not recorded | 6a0405bfdbc836b87d827743 | | VCD | 13.9 | Not recorded | 6a0405bfdbc836b87d827743 | ### LaSCD fACC: 22.2. Result ID: 6a043b1747f34ce924ea3211. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen-VL"}. This record does not assert independent reproduction. ### DeCo fACC: 20.2. Result ID: 6a043b1747f34ce924ea3210. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen-VL"}. This record does not assert independent reproduction. ### Qwen-VL fACC: 19.9. Result ID: 6a043b1747f34ce924ea320f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Base Model":"Qwen-VL"}. This record does not assert independent reproduction. ### LLaVA-1.5 fACC: 17.9. Result ID: 6a043b1747f34ce924ea3208. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Base Model":"LLaVA-1.5"}. This record does not assert independent reproduction. ### MemVR fACC: 17.9. Result ID: 6a043b1747f34ce924ea320d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"LLaVA-1.5"}. This record does not assert independent reproduction. ### OPERA fACC: 16.2. Result ID: 6a043b1747f34ce924ea3209. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Base Model":"LLaVA-1.5"}. This record does not assert independent reproduction. ### LaSCD fACC: 15.8. Result ID: 6a043b1747f34ce924ea320e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"LLaVA-1.5"}. This record does not assert independent reproduction. ### DeCo fACC: 15.3. Result ID: 6a043b1747f34ce924ea320c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"LLaVA-1.5"}. This record does not assert independent reproduction. ### ICD fACC: 13.9. Result ID: 6a043b1747f34ce924ea320a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"LLaVA-1.5"}. This record does not assert independent reproduction. ### VCD fACC: 13.9. Result ID: 6a043b1747f34ce924ea320b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"LLaVA-1.5"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.