# Hallucination Evaluation on POPE Popular MSCOCO, A-OKVQA, GQA average Source: [Hallucination Evaluation on POPE Popular MSCOCO, A-OKVQA, GQA average]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:32:52.654Z Average performance across models evaluated for object hallucination using the POPE methodology on the Popular subset of MSCOCO, A-OKVQA, and GQA datasets. 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) | POPE Popular MSCOCO, A-OKVQA, GQA average | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 15 of 15 | | 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. - [Precision](): Higher is better; unit: PERCENT. - [Recall](): Higher is better; unit: PERCENT. - [F1 Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Vanilla | 88.48 | Not recorded | 6993f5e69ebc499c974098f1 | | PAI | 88.45 | Not recorded | 6993f5e69ebc499c974098f1 | | AdaVBoost | 88.35 | Not recorded | 6993f5e69ebc499c974098f1 | | VGA | 87.46 | Not recorded | 6993f5e69ebc499c974098f1 | | VAF | 87.14 | Not recorded | 6993f5e69ebc499c974098f1 | | Vanilla | 86.01 | Not recorded | 6993f5e69ebc499c974098f1 | | AdaVBoost | 86.01 | Not recorded | 6993f5e69ebc499c974098f1 | | VAF | 84.64 | Not recorded | 6993f5e69ebc499c974098f1 | | PAI | 84.09 | Not recorded | 6993f5e69ebc499c974098f1 | | VGA | 83.45 | Not recorded | 6993f5e69ebc499c974098f1 | | VGA | 83.31 | Not recorded | 6993f5e69ebc499c974098f1 | | Vanilla | 82.85 | Not recorded | 6993f5e69ebc499c974098f1 | | VAF | 82.84 | Not recorded | 6993f5e69ebc499c974098f1 | | AdaVBoost | 82.64 | Not recorded | 6993f5e69ebc499c974098f1 | | PAI | 81.28 | Not recorded | 6993f5e69ebc499c974098f1 | ### Vanilla Accuracy: 88.48. Result ID: 699a77af5698665ec400e44a. [Reporting paper]() Recorded evaluation configuration: {"MLLM":"Qwen3-VL"}. This record does not assert independent reproduction. ### PAI Accuracy: 88.45. Result ID: 699a77af5698665ec400e44b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MLLM":"Qwen3-VL"}. This record does not assert independent reproduction. ### AdaVBoost Accuracy: 88.35. Result ID: 699a77af5698665ec400e44e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MLLM":"Qwen3-VL"}. This record does not assert independent reproduction. ### VGA Accuracy: 87.46. Result ID: 699a77af5698665ec400e44d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MLLM":"Qwen3-VL"}. This record does not assert independent reproduction. ### VAF Accuracy: 87.14. Result ID: 699a77af5698665ec400e44c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"MLLM":"Qwen3-VL"}. This record does not assert independent reproduction. ### Vanilla Accuracy: 86.01. Result ID: 699a77af5698665ec400e445. [Reporting paper]() Recorded evaluation configuration: {"MLLM":"LLaVA-NeXT"}. This record does not assert independent reproduction. ### AdaVBoost Accuracy: 86.01. Result ID: 699a77af5698665ec400e449. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MLLM":"LLaVA-NeXT"}. This record does not assert independent reproduction. ### VAF Accuracy: 84.64. Result ID: 699a77af5698665ec400e447. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"MLLM":"LLaVA-NeXT"}. This record does not assert independent reproduction. ### PAI Accuracy: 84.09. Result ID: 699a77af5698665ec400e446. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MLLM":"LLaVA-NeXT"}. This record does not assert independent reproduction. ### VGA Accuracy: 83.45. Result ID: 699a77af5698665ec400e448. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MLLM":"LLaVA-NeXT"}. This record does not assert independent reproduction. ### VGA Accuracy: 83.31. Result ID: 699a77af5698665ec400e452. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MLLM":"InternVL3.5"}. This record does not assert independent reproduction. ### Vanilla Accuracy: 82.85. Result ID: 699a77af5698665ec400e44f. [Reporting paper]() Recorded evaluation configuration: {"MLLM":"InternVL3.5"}. This record does not assert independent reproduction. ### VAF Accuracy: 82.84. Result ID: 699a77af5698665ec400e451. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"MLLM":"InternVL3.5"}. This record does not assert independent reproduction. ### AdaVBoost Accuracy: 82.64. Result ID: 699a77af5698665ec400e453. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MLLM":"InternVL3.5"}. This record does not assert independent reproduction. ### PAI Accuracy: 81.28. Result ID: 699a77af5698665ec400e450. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MLLM":"InternVL3.5"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.