# Object Hallucination Evaluation on CHAIR (val) Source: [Object Hallucination Evaluation on CHAIR (val)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:38:20.143Z Evaluation of object hallucination detection performance on the validation split of the CHAIR dataset, measured using CHAIRs, CHAIRi, 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 | Object Hallucination Evaluation | | Dataset (including any stated split) | CHAIR (val) | | Metric | CHAIRs Score | | 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 - [CHAIRs Score](): Higher is better; unit: PERCENT. - [CHAIRi Score](): Higher is better; unit: PERCENT. - [F1 Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | CHAIRs Score | Result date | Report paper | | --- | --- | --- | --- | | Vanilla | 58.8 | Not recorded | 6993f5e69ebc499c974098f1 | | VGA | 58.4 | Not recorded | 6993f5e69ebc499c974098f1 | | PAI | 53.6 | Not recorded | 6993f5e69ebc499c974098f1 | | VAF | 53.6 | Not recorded | 6993f5e69ebc499c974098f1 | | AdaVBoost | 46 | Not recorded | 6993f5e69ebc499c974098f1 | | PAI | 45.6 | Not recorded | 6993f5e69ebc499c974098f1 | | VGA | 44.2 | Not recorded | 6993f5e69ebc499c974098f1 | | VAF | 42.2 | Not recorded | 6993f5e69ebc499c974098f1 | | Vanilla | 41.4 | Not recorded | 6993f5e69ebc499c974098f1 | | PAI | 39.6 | Not recorded | 6993f5e69ebc499c974098f1 | | VAF | 36.4 | Not recorded | 6993f5e69ebc499c974098f1 | | AdaVBoost | 34.4 | Not recorded | 6993f5e69ebc499c974098f1 | | Vanilla | 33.8 | Not recorded | 6993f5e69ebc499c974098f1 | | VGA | 32.4 | Not recorded | 6993f5e69ebc499c974098f1 | | AdaVBoost | 28.8 | Not recorded | 6993f5e69ebc499c974098f1 | ### Vanilla CHAIRs Score: 58.8. Result ID: 699a77af5698665ec400e486. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-VL"}. This record does not assert independent reproduction. ### VGA CHAIRs Score: 58.4. Result ID: 699a77af5698665ec400e489. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-VL"}. This record does not assert independent reproduction. ### PAI CHAIRs Score: 53.6. Result ID: 699a77af5698665ec400e487. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-VL"}. This record does not assert independent reproduction. ### VAF CHAIRs Score: 53.6. Result ID: 699a77af5698665ec400e488. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen3-VL"}. This record does not assert independent reproduction. ### AdaVBoost CHAIRs Score: 46. Result ID: 699a77af5698665ec400e48a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-VL"}. This record does not assert independent reproduction. ### PAI CHAIRs Score: 45.6. Result ID: 699a77af5698665ec400e48c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"InternVL3.5"}. This record does not assert independent reproduction. ### VGA CHAIRs Score: 44.2. Result ID: 699a77af5698665ec400e48e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"InternVL3.5"}. This record does not assert independent reproduction. ### VAF CHAIRs Score: 42.2. Result ID: 699a77af5698665ec400e48d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"InternVL3.5"}. This record does not assert independent reproduction. ### Vanilla CHAIRs Score: 41.4. Result ID: 699a77af5698665ec400e48b. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"InternVL3.5"}. This record does not assert independent reproduction. ### PAI CHAIRs Score: 39.6. Result ID: 699a77af5698665ec400e482. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LLaVA-NeXT"}. This record does not assert independent reproduction. ### VAF CHAIRs Score: 36.4. Result ID: 699a77af5698665ec400e483. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"LLaVA-NeXT"}. This record does not assert independent reproduction. ### AdaVBoost CHAIRs Score: 34.4. Result ID: 699a77af5698665ec400e48f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"InternVL3.5"}. This record does not assert independent reproduction. ### Vanilla CHAIRs Score: 33.8. Result ID: 699a77af5698665ec400e481. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"LLaVA-NeXT"}. This record does not assert independent reproduction. ### VGA CHAIRs Score: 32.4. Result ID: 699a77af5698665ec400e484. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LLaVA-NeXT"}. This record does not assert independent reproduction. ### AdaVBoost CHAIRs Score: 28.8. Result ID: 699a77af5698665ec400e485. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LLaVA-NeXT"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.