# Prompt Adherence Evaluation on DB-3DME 1.0 (test) Source: [Prompt Adherence Evaluation on DB-3DME 1.0 (test)]() Collection index: [llms.txt]() Data updated: 2026-06-11T07:15:07.810Z Evaluation of model performance on the Prompt Adherence Evaluation task using the test split of the DB-3DME 1.0 dataset, measured by Exact-Match, Within-One, and Pearson correlation. 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 | Prompt Adherence Evaluation | | Dataset (including any stated split) | DB-3DME 1.0 (test) | | Metric | Pearson R | | Unit | SCALAR | | 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 - [Pearson R](): Higher is better; unit: SCALAR. - [Exact-Match Accuracy](): Higher is better; unit: PERCENT. - [Within-One Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Pearson R | Result date | Report paper | | --- | --- | --- | --- | | ChatGPT-5-high | 0.483 | Not recorded | 6a28f34e90966ade919c17ff | | ChatGPT-5-low | 0.472 | Not recorded | 6a28f34e90966ade919c17ff | | ChatGPT-5-medium | 0.468 | Not recorded | 6a28f34e90966ade919c17ff | | ChatGPT-5-high | 0.459 | Not recorded | 6a28f34e90966ade919c17ff | | Gemini-2.5-pro | 0.454 | Not recorded | 6a28f34e90966ade919c17ff | | Gemini-2.5-pro | 0.452 | Not recorded | 6a28f34e90966ade919c17ff | | ChatGPT-5-medium | 0.451 | Not recorded | 6a28f34e90966ade919c17ff | | ChatGPT-5-low | 0.427 | Not recorded | 6a28f34e90966ade919c17ff | | ChatGPT-4o | 0.414 | Not recorded | 6a28f34e90966ade919c17ff | | ChatGPT-4o | 0.413 | Not recorded | 6a28f34e90966ade919c17ff | | ChatGPT-4.1 | 0.404 | Not recorded | 6a28f34e90966ade919c17ff | | ChatGPT-4.1 | 0.393 | Not recorded | 6a28f34e90966ade919c17ff | | Qwen-2.5-vl-7b | 0.232 | Not recorded | 6a28f34e90966ade919c17ff | | CLIP Score (ViT-L/14) | 0.228 | Not recorded | 6a28f34e90966ade919c17ff | | Qwen-2.5-vl-7b | 0.214 | Not recorded | 6a28f34e90966ade919c17ff | ### ChatGPT-5-high Pearson R: 0.483. Result ID: 6a2a5ecdfbc373592c26f87c. [Reporting paper]() Recorded evaluation configuration: {"Prompting Version":"V2"}. This record does not assert independent reproduction. ### ChatGPT-5-low Pearson R: 0.472. Result ID: 6a2a5ecdfbc373592c26f87e. [Reporting paper]() Recorded evaluation configuration: {"Prompting Version":"V2"}. This record does not assert independent reproduction. ### ChatGPT-5-medium Pearson R: 0.468. Result ID: 6a2a5ecdfbc373592c26f87d. [Reporting paper]() Recorded evaluation configuration: {"Prompting Version":"V2"}. This record does not assert independent reproduction. ### ChatGPT-5-high Pearson R: 0.459. Result ID: 6a2a5ecdfbc373592c26f875. [Reporting paper]() Recorded evaluation configuration: {"Prompting Version":"V1"}. This record does not assert independent reproduction. ### Gemini-2.5-pro Pearson R: 0.454. Result ID: 6a2a5ecdfbc373592c26f879. [Reporting paper]() Recorded evaluation configuration: {"Prompting Version":"V1"}. This record does not assert independent reproduction. ### Gemini-2.5-pro Pearson R: 0.452. Result ID: 6a2a5ecdfbc373592c26f880. [Reporting paper]() Recorded evaluation configuration: {"Prompting Version":"V2"}. This record does not assert independent reproduction. ### ChatGPT-5-medium Pearson R: 0.451. Result ID: 6a2a5ecdfbc373592c26f876. [Reporting paper]() Recorded evaluation configuration: {"Prompting Version":"V1"}. This record does not assert independent reproduction. ### ChatGPT-5-low Pearson R: 0.427. Result ID: 6a2a5ecdfbc373592c26f877. [Reporting paper]() Recorded evaluation configuration: {"Prompting Version":"V1"}. This record does not assert independent reproduction. ### ChatGPT-4o Pearson R: 0.414. Result ID: 6a2a5ecdfbc373592c26f873. [Reporting paper]() Recorded evaluation configuration: {"Prompting Version":"V1"}. This record does not assert independent reproduction. ### ChatGPT-4o Pearson R: 0.413. Result ID: 6a2a5ecdfbc373592c26f87a. [Reporting paper]() Recorded evaluation configuration: {"Prompting Version":"V2"}. This record does not assert independent reproduction. ### ChatGPT-4.1 Pearson R: 0.404. Result ID: 6a2a5ecdfbc373592c26f87f. [Reporting paper]() Recorded evaluation configuration: {"Prompting Version":"V2"}. This record does not assert independent reproduction. ### ChatGPT-4.1 Pearson R: 0.393. Result ID: 6a2a5ecdfbc373592c26f878. [Reporting paper]() Recorded evaluation configuration: {"Prompting Version":"V1"}. This record does not assert independent reproduction. ### Qwen-2.5-vl-7b Pearson R: 0.232. Result ID: 6a2a5ecdfbc373592c26f874. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompting Version":"V1"}. This record does not assert independent reproduction. ### CLIP Score (ViT-L/14) Pearson R: 0.228. Result ID: 6a2a5ecdfbc373592c26f872. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"Non-VLM baseline"}. This record does not assert independent reproduction. ### Qwen-2.5-vl-7b Pearson R: 0.214. Result ID: 6a2a5ecdfbc373592c26f87b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompting Version":"V2"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.