# General Visual Question Answering on SEED-Bench IMG 2023a Source: [General Visual Question Answering on SEED-Bench IMG 2023a]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:30:38.045Z Evaluation of model performance on the specific 2023a image subset of the SEED-Bench dataset for General Visual Question Answering tasks, typically measured by Accuracy. 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 | General Visual Question Answering | | Dataset (including any stated split) | SEED-Bench IMG 2023a | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 13 of 13 | | 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. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | InternVL2.5 | 77 | Not recorded | 68fa793e1e209131cea7cd66 | | InternVL2.5-MPO | 76.9 | Not recorded | 68fa793e1e209131cea7cd66 | | DeepSeekVL-2-Small | 76.8 | Not recorded | 68fa793e1e209131cea7cd66 | | SAIL-VL-8B | 75.5 | Not recorded | 68fa793e1e209131cea7cd66 | | InternVL2 | 75.4 | Not recorded | 68fa793e1e209131cea7cd66 | | Qwen2-VL | 75.3 | Not recorded | 68fa793e1e209131cea7cd66 | | SAIL-VL | 74.7 | Not recorded | 68fa793e1e209131cea7cd66 | | Aquila | 73.9 | Not recorded | 68fa793e1e209131cea7cd66 | | InternVL2.5 | 73.4 | Not recorded | 68fa793e1e209131cea7cd66 | | InternVL2.5-MPO | 73.2 | Not recorded | 68fa793e1e209131cea7cd66 | | DeepSeekVL-2-Tiny | 72.5 | Not recorded | 68fa793e1e209131cea7cd66 | | Qwen2-VL | 72 | Not recorded | 68fa793e1e209131cea7cd66 | | InternVL2 | 70.9 | Not recorded | 68fa793e1e209131cea7cd66 | ### InternVL2.5 Accuracy: 77. Result ID: 6995d6823badfaffe6dc4678. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### InternVL2.5-MPO Accuracy: 76.9. Result ID: 6995d6823badfaffe6dc4679. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### DeepSeekVL-2-Small Accuracy: 76.8. Result ID: 6995d6823badfaffe6dc467a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### SAIL-VL-8B Accuracy: 75.5. Result ID: 6995d6823badfaffe6dc4675. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### InternVL2 Accuracy: 75.4. Result ID: 6995d6823badfaffe6dc4677. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen2-VL Accuracy: 75.3. Result ID: 6995d6823badfaffe6dc4676. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### SAIL-VL Accuracy: 74.7. Result ID: 6995d6823badfaffe6dc46e5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Aquila Accuracy: 73.9. Result ID: 6995d6823badfaffe6dc46ea. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### InternVL2.5 Accuracy: 73.4. Result ID: 6995d6823badfaffe6dc46e8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### InternVL2.5-MPO Accuracy: 73.2. Result ID: 6995d6823badfaffe6dc46e9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Strategy":"MPO"}. This record does not assert independent reproduction. ### DeepSeekVL-2-Tiny Accuracy: 72.5. Result ID: 6995d6823badfaffe6dc46eb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen2-VL Accuracy: 72. Result ID: 6995d6823badfaffe6dc46e6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### InternVL2 Accuracy: 70.9. Result ID: 6995d6823badfaffe6dc46e7. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.