# Scientific Image Quality Assessment on SIQA-S 1.0 (test) Source: [Scientific Image Quality Assessment on SIQA-S 1.0 (test)]() Collection index: [llms.txt]() Data updated: 2026-03-10T08:00:30.649Z Evaluation of Scientific Image Quality Assessment performance on the test split of the SIQA-S 1.0 dataset, reporting correlation metrics (SRCC, PLCC) broken down by Perception, Knowledge, and Overall 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 | Scientific Image Quality Assessment | | Dataset (including any stated split) | SIQA-S 1.0 (test) | | Metric | Perception SRCC | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 12 of 12 | | 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 - [Perception SRCC](): Higher is better; unit: SCALAR. - [Perception PLCC](): Higher is better; unit: SCALAR. - [Knowledge SRCC](): Higher is better; unit: SCALAR. - [Knowledge PLCC](): Higher is better; unit: SCALAR. - [Overall SRCC](): Higher is better; unit: SCALAR. - [Overall PLCC](): Higher is better; unit: SCALAR. ## Recorded results | Method | Perception SRCC | Result date | Report paper | | --- | --- | --- | --- | | SIQA-Judger | 0.857 | Not recorded | 69afa57f2d603e6de3e43a08 | | HyperIQA | 0.773 | Not recorded | 69afa57f2d603e6de3e43a08 | | Q-Align | 0.749 | Not recorded | 69afa57f2d603e6de3e43a08 | | CLIP-IQA+ | 0.724 | Not recorded | 69afa57f2d603e6de3e43a08 | | GPT-4o | 0.694 | Not recorded | 69afa57f2d603e6de3e43a08 | | Qwen3-VL-235B | 0.629 | Not recorded | 69afa57f2d603e6de3e43a08 | | InternVL3.5-241B | 0.6 | Not recorded | 69afa57f2d603e6de3e43a08 | | Doubao-1.5-Vision-Pro | 0.596 | Not recorded | 69afa57f2d603e6de3e43a08 | | Llama-3.2-90B-Vision | 0.568 | Not recorded | 69afa57f2d603e6de3e43a08 | | CLIP-IQA | 0.496 | Not recorded | 69afa57f2d603e6de3e43a08 | | GPT-3.5-turbo | 0.48 | Not recorded | 69afa57f2d603e6de3e43a08 | | NIQE | 0.345 | Not recorded | 69afa57f2d603e6de3e43a08 | ### SIQA-Judger Perception SRCC: 0.857. Result ID: 69afce976dbb7075b957edd2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"trained"}. This record does not assert independent reproduction. ### HyperIQA Perception SRCC: 0.773. Result ID: 69afce976dbb7075b957edd1. [Reporting paper]() Recorded evaluation configuration: {"Model Category":"Natural IQA","Evaluation Protocol":"trained"}. This record does not assert independent reproduction. ### Q-Align Perception SRCC: 0.749. Result ID: 69afce976dbb7075b957edce. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"Natural IQA","Evaluation Protocol":"zero-shot"}. This record does not assert independent reproduction. ### CLIP-IQA+ Perception SRCC: 0.724. Result ID: 69afce976dbb7075b957edd0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"Natural IQA","Evaluation Protocol":"trained"}. This record does not assert independent reproduction. ### GPT-4o Perception SRCC: 0.694. Result ID: 69afce976dbb7075b957edc7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Closed-Source MLLM","Evaluation Protocol":"zero-shot"}. This record does not assert independent reproduction. ### Qwen3-VL-235B Perception SRCC: 0.629. Result ID: 69afce976dbb7075b957edcc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Open-Source MLLM","Evaluation Protocol":"zero-shot"}. This record does not assert independent reproduction. ### InternVL3.5-241B Perception SRCC: 0.6. Result ID: 69afce976dbb7075b957edcb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Open-Source MLLM","Evaluation Protocol":"zero-shot"}. This record does not assert independent reproduction. ### Doubao-1.5-Vision-Pro Perception SRCC: 0.596. Result ID: 69afce976dbb7075b957edc9. [Reporting paper]() Recorded evaluation configuration: {"Model Category":"Closed-Source MLLM","Evaluation Protocol":"zero-shot"}. This record does not assert independent reproduction. ### Llama-3.2-90B-Vision Perception SRCC: 0.568. Result ID: 69afce976dbb7075b957edca. [Reporting paper]() Recorded evaluation configuration: {"Model Category":"Open-Source MLLM","Evaluation Protocol":"zero-shot"}. This record does not assert independent reproduction. ### CLIP-IQA Perception SRCC: 0.496. Result ID: 69afce976dbb7075b957edcf. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"Natural IQA","Evaluation Protocol":"zero-shot"}. This record does not assert independent reproduction. ### GPT-3.5-turbo Perception SRCC: 0.48. Result ID: 69afce976dbb7075b957edc8. [Reporting paper]() Recorded evaluation configuration: {"Model Category":"Closed-Source MLLM","Evaluation Protocol":"zero-shot"}. This record does not assert independent reproduction. ### NIQE Perception SRCC: 0.345. Result ID: 69afce976dbb7075b957edcd. [Reporting paper]() Recorded evaluation configuration: {"Model Category":"Natural IQA","Evaluation Protocol":"zero-shot"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.