# Self-evaluation on MMVet (AUROC) Source: [Self-evaluation on MMVet (AUROC)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:26:22.997Z Evaluation of model performance on the MMVet dataset specifically measuring the Area Under the Receiver Operating Characteristic curve (AUROC). 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 | Self-evaluation | | Dataset (including any stated split) | MMVet | | Metric | AUROC | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 36 of 36 | | 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 - [AUROC](): Higher is better; unit: SCALAR. ## Recorded results | Method | AUROC | Result date | Report paper | | --- | --- | --- | --- | | VAUQ | 0.886 | Not recorded | 699e82176017c4460ffacfdf | | Semantic Entropy | 0.864 | Not recorded | 699e82176017c4460ffacfdf | | VL-Uncertainty | 0.859 | Not recorded | 699e82176017c4460ffacfdf | | EigenScore | 0.851 | Not recorded | 699e82176017c4460ffacfdf | | VL-Uncertainty | 0.823 | Not recorded | 699e82176017c4460ffacfdf | | VAUQ | 0.815 | Not recorded | 699e82176017c4460ffacfdf | | Semantic Entropy | 0.813 | Not recorded | 699e82176017c4460ffacfdf | | Perplexity | 0.813 | Not recorded | 699e82176017c4460ffacfdf | | Perplexity | 0.793 | Not recorded | 699e82176017c4460ffacfdf | | VAUQ | 0.783 | Not recorded | 699e82176017c4460ffacfdf | | EigenScore | 0.782 | Not recorded | 699e82176017c4460ffacfdf | | Perplexity | 0.766 | Not recorded | 699e82176017c4460ffacfdf | | VAUQ | 0.758 | Not recorded | 699e82176017c4460ffacfdf | | VL-Uncertainty | 0.757 | Not recorded | 699e82176017c4460ffacfdf | | Verbalized | 0.717 | Not recorded | 699e82176017c4460ffacfdf | | Contextual Lens | 0.708 | Not recorded | 699e82176017c4460ffacfdf | | Semantic Entropy | 0.704 | Not recorded | 699e82176017c4460ffacfdf | | VL-Uncertainty | 0.697 | Not recorded | 699e82176017c4460ffacfdf | | Perplexity | 0.675 | Not recorded | 699e82176017c4460ffacfdf | | Verbalized | 0.672 | Not recorded | 699e82176017c4460ffacfdf | | Contextual Lens | 0.655 | Not recorded | 699e82176017c4460ffacfdf | | EigenScore | 0.641 | Not recorded | 699e82176017c4460ffacfdf | | Contextual Lens | 0.614 | Not recorded | 699e82176017c4460ffacfdf | | Chain-of-Embeddings | 0.608 | Not recorded | 699e82176017c4460ffacfdf | | EigenScore | 0.608 | Not recorded | 699e82176017c4460ffacfdf | | Semantic Entropy | 0.601 | Not recorded | 699e82176017c4460ffacfdf | | Chain-of-Embeddings | 0.598 | Not recorded | 699e82176017c4460ffacfdf | | Contextual Lens | 0.596 | Not recorded | 699e82176017c4460ffacfdf | | Verbalized | 0.594 | Not recorded | 699e82176017c4460ffacfdf | | SVAR | 0.546 | Not recorded | 699e82176017c4460ffacfdf | | Chain-of-Embeddings | 0.528 | Not recorded | 699e82176017c4460ffacfdf | | Verbalized | 0.519 | Not recorded | 699e82176017c4460ffacfdf | | SVAR | 0.497 | Not recorded | 699e82176017c4460ffacfdf | | Chain-of-Embeddings | 0.444 | Not recorded | 699e82176017c4460ffacfdf | | SVAR | 0.342 | Not recorded | 699e82176017c4460ffacfdf | | SVAR | 0.293 | Not recorded | 699e82176017c4460ffacfdf | ### VAUQ AUROC: 0.886. Result ID: 699ebf025698665ec48e9007. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LLaVA-1.5-13B"}. This record does not assert independent reproduction. ### Semantic Entropy AUROC: 0.864. Result ID: 699ebf025698665ec48e9005. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LLaVA-1.5-13B"}. This record does not assert independent reproduction. ### VL-Uncertainty AUROC: 0.859. Result ID: 699ebf025698665ec48e9006. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LLaVA-1.5-13B"}. This record does not assert independent reproduction. ### EigenScore AUROC: 0.851. Result ID: 699ebf025698665ec48e9004. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LLaVA-1.5-13B"}. This record does not assert independent reproduction. ### VL-Uncertainty AUROC: 0.823. Result ID: 699ebf025698665ec48e8ffd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LLaVA-1.5-7B"}. This record does not assert independent reproduction. ### VAUQ AUROC: 0.815. Result ID: 699ebf025698665ec48e8ffe. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LLaVA-1.5-7B"}. This record does not assert independent reproduction. ### Semantic Entropy AUROC: 0.813. Result ID: 699ebf025698665ec48e8ffc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LLaVA-1.5-7B"}. This record does not assert independent reproduction. ### Perplexity AUROC: 0.813. Result ID: 699ebf025698665ec48e8fff. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LLaVA-1.5-13B"}. This record does not assert independent reproduction. ### Perplexity AUROC: 0.793. Result ID: 699ebf025698665ec48e8ff6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LLaVA-1.5-7B"}. This record does not assert independent reproduction. ### VAUQ AUROC: 0.783. Result ID: 699ebf025698665ec48e9046. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen-2.5-VL-7B"}. This record does not assert independent reproduction. ### EigenScore AUROC: 0.782. Result ID: 699ebf025698665ec48e8ffb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LLaVA-1.5-7B"}. This record does not assert independent reproduction. ### Perplexity AUROC: 0.766. Result ID: 699ebf025698665ec48e903e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen-2.5-VL-7B"}. This record does not assert independent reproduction. ### VAUQ AUROC: 0.758. Result ID: 699ebf025698665ec48e904f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"InternVL3.5-8B"}. This record does not assert independent reproduction. ### VL-Uncertainty AUROC: 0.757. Result ID: 699ebf025698665ec48e904e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"InternVL3.5-8B"}. This record does not assert independent reproduction. ### Verbalized AUROC: 0.717. Result ID: 699ebf025698665ec48e8ff7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LLaVA-1.5-7B"}. This record does not assert independent reproduction. ### Contextual Lens AUROC: 0.708. Result ID: 699ebf025698665ec48e8ff9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LLaVA-1.5-7B"}. This record does not assert independent reproduction. ### Semantic Entropy AUROC: 0.704. Result ID: 699ebf025698665ec48e904d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"InternVL3.5-8B"}. This record does not assert independent reproduction. ### VL-Uncertainty AUROC: 0.697. Result ID: 699ebf025698665ec48e9045. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen-2.5-VL-7B"}. This record does not assert independent reproduction. ### Perplexity AUROC: 0.675. Result ID: 699ebf025698665ec48e9047. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"InternVL3.5-8B"}. This record does not assert independent reproduction. ### Verbalized AUROC: 0.672. Result ID: 699ebf025698665ec48e9000. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LLaVA-1.5-13B"}. This record does not assert independent reproduction. ### Contextual Lens AUROC: 0.655. Result ID: 699ebf025698665ec48e9041. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen-2.5-VL-7B"}. This record does not assert independent reproduction. ### EigenScore AUROC: 0.641. Result ID: 699ebf025698665ec48e904c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"InternVL3.5-8B"}. This record does not assert independent reproduction. ### Contextual Lens AUROC: 0.614. Result ID: 699ebf025698665ec48e9002. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LLaVA-1.5-13B"}. This record does not assert independent reproduction. ### Chain-of-Embeddings AUROC: 0.608. Result ID: 699ebf025698665ec48e8ffa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LLaVA-1.5-7B"}. This record does not assert independent reproduction. ### EigenScore AUROC: 0.608. Result ID: 699ebf025698665ec48e9043. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen-2.5-VL-7B"}. This record does not assert independent reproduction. ### Semantic Entropy AUROC: 0.601. Result ID: 699ebf025698665ec48e9044. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen-2.5-VL-7B"}. This record does not assert independent reproduction. ### Chain-of-Embeddings AUROC: 0.598. Result ID: 699ebf025698665ec48e9042. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen-2.5-VL-7B"}. This record does not assert independent reproduction. ### Contextual Lens AUROC: 0.596. Result ID: 699ebf025698665ec48e904a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"InternVL3.5-8B"}. This record does not assert independent reproduction. ### Verbalized AUROC: 0.594. Result ID: 699ebf025698665ec48e9048. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"InternVL3.5-8B"}. This record does not assert independent reproduction. ### SVAR AUROC: 0.546. Result ID: 699ebf025698665ec48e9040. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen-2.5-VL-7B"}. This record does not assert independent reproduction. ### Chain-of-Embeddings AUROC: 0.528. Result ID: 699ebf025698665ec48e904b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"InternVL3.5-8B"}. This record does not assert independent reproduction. ### Verbalized AUROC: 0.519. Result ID: 699ebf025698665ec48e903f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen-2.5-VL-7B"}. This record does not assert independent reproduction. ### SVAR AUROC: 0.497. Result ID: 699ebf025698665ec48e9049. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"InternVL3.5-8B"}. This record does not assert independent reproduction. ### Chain-of-Embeddings AUROC: 0.444. Result ID: 699ebf025698665ec48e9003. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LLaVA-1.5-13B"}. This record does not assert independent reproduction. ### SVAR AUROC: 0.342. Result ID: 699ebf025698665ec48e9001. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LLaVA-1.5-13B"}. This record does not assert independent reproduction. ### SVAR AUROC: 0.293. Result ID: 699ebf025698665ec48e8ff8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LLaVA-1.5-7B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.