# Hallucination Evaluation on POPE MSCOCO, A-OKVQA, GQA average (Random) Source: [Hallucination Evaluation on POPE MSCOCO, A-OKVQA, GQA average (Random)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:32:52.636Z Average performance across models evaluated using the POPE methodology (Random setting) on the MSCOCO, A-OKVQA, and GQA datasets for hallucination detection, reporting Accuracy, Precision, Recall, and F1 scores. 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 MSCOCO, A-OKVQA, GQA average (Random) | | 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 | 93.24 | Not recorded | 6993f5e69ebc499c974098f1 | | PAI | 93.23 | Not recorded | 6993f5e69ebc499c974098f1 | | AdaVBoost | 93.16 | Not recorded | 6993f5e69ebc499c974098f1 | | VAF | 93.1 | Not recorded | 6993f5e69ebc499c974098f1 | | VGA | 92.82 | Not recorded | 6993f5e69ebc499c974098f1 | | VGA | 92.32 | Not recorded | 6993f5e69ebc499c974098f1 | | VAF | 91.7 | Not recorded | 6993f5e69ebc499c974098f1 | | Vanilla | 91.34 | Not recorded | 6993f5e69ebc499c974098f1 | | AdaVBoost | 91.33 | Not recorded | 6993f5e69ebc499c974098f1 | | AdaVBoost | 91.26 | Not recorded | 6993f5e69ebc499c974098f1 | | Vanilla | 90.96 | Not recorded | 6993f5e69ebc499c974098f1 | | VGA | 90.83 | Not recorded | 6993f5e69ebc499c974098f1 | | PAI | 90.36 | Not recorded | 6993f5e69ebc499c974098f1 | | VAF | 90.24 | Not recorded | 6993f5e69ebc499c974098f1 | | PAI | 90.17 | Not recorded | 6993f5e69ebc499c974098f1 | ### Vanilla Accuracy: 93.24. Result ID: 699a77af5698665ec400e43b. [Reporting paper]() Recorded evaluation configuration: {"MLLM":"Qwen3-VL"}. This record does not assert independent reproduction. ### PAI Accuracy: 93.23. Result ID: 699a77af5698665ec400e43c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MLLM":"Qwen3-VL"}. This record does not assert independent reproduction. ### AdaVBoost Accuracy: 93.16. Result ID: 699a77af5698665ec400e43f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MLLM":"Qwen3-VL"}. This record does not assert independent reproduction. ### VAF Accuracy: 93.1. Result ID: 699a77af5698665ec400e43d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"MLLM":"Qwen3-VL"}. This record does not assert independent reproduction. ### VGA Accuracy: 92.82. Result ID: 699a77af5698665ec400e43e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MLLM":"Qwen3-VL"}. This record does not assert independent reproduction. ### VGA Accuracy: 92.32. Result ID: 699a77af5698665ec400e443. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MLLM":"InternVL3.5"}. This record does not assert independent reproduction. ### VAF Accuracy: 91.7. Result ID: 699a77af5698665ec400e442. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"MLLM":"InternVL3.5"}. This record does not assert independent reproduction. ### Vanilla Accuracy: 91.34. Result ID: 699a77af5698665ec400e436. [Reporting paper]() Recorded evaluation configuration: {"MLLM":"LLaVA-NeXT"}. This record does not assert independent reproduction. ### AdaVBoost Accuracy: 91.33. Result ID: 699a77af5698665ec400e43a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MLLM":"LLaVA-NeXT"}. This record does not assert independent reproduction. ### AdaVBoost Accuracy: 91.26. Result ID: 699a77af5698665ec400e444. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MLLM":"InternVL3.5"}. This record does not assert independent reproduction. ### Vanilla Accuracy: 90.96. Result ID: 699a77af5698665ec400e440. [Reporting paper]() Recorded evaluation configuration: {"MLLM":"InternVL3.5"}. This record does not assert independent reproduction. ### VGA Accuracy: 90.83. Result ID: 699a77af5698665ec400e439. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MLLM":"LLaVA-NeXT"}. This record does not assert independent reproduction. ### PAI Accuracy: 90.36. Result ID: 699a77af5698665ec400e437. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MLLM":"LLaVA-NeXT"}. This record does not assert independent reproduction. ### VAF Accuracy: 90.24. Result ID: 699a77af5698665ec400e438. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"MLLM":"LLaVA-NeXT"}. This record does not assert independent reproduction. ### PAI Accuracy: 90.17. Result ID: 699a77af5698665ec400e441. [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.