SeedBench
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Multimodal Understanding | SEEDBench2 Plus | Accuracy76.86 | 138 | |
| Visual Question Answering | SeedBench | Accuracy66.1 | 19 | |
| Comprehensive Evaluation | SeedBench (all) | Score76.8 | 19 | |
| Complex Scene Reasoning | SEEDBench | Accuracy (All)77.03 | 17 | |
| Visual Perception | SeedBench-2-Plus | Accuracy72 | 15 | |
| Multidisciplinary Knowledge | SeedBench | Score76.4 | 15 | |
| Visual Question Answering | SeedBench | Average Score78.9 | 13 | |
| Multimodal QA | SEEDBench (test) | SEEDBench Score33.7 | 13 | |
| MM General VQA | SEEDBench IMG | Accuracy80.4 | 12 | |
| Multimodal Understanding | SeedBench image | Score76.7 | 12 | |
| General Visual Understanding | SeedBench 2+ | SeedBench2+ Score67.7 | 11 | |
| Visual Question Answering | SeedBench Avg | Accuracy77.96 | 11 | |
| Multi-discipline Video Understanding | SeedBench video | Accuracy62.1 | 11 | |
| Multimodal Understanding | SeedBench-2 | Score81 | 10 | |
| General MCQA | SeedBench | Score71.5 | 9 | |
| Short-answer Visual Question Answering | SEEDBench2+ | Accuracy68.7 | 9 | |
| Multimodal Evaluation | SeedBench | SeedBench Score78 | 8 | |
| Visual Question Answering | SEEDBench | BD-Rate-23.78 | 8 | |
| Multimodal Evaluation | SeedBench (all) | Score61.82 | 8 | |
| Video Understanding | SeedBench | SeedBench Score57 | 7 | |
| Visual Question Answering | SeedBench 2 | Average Score60.5 | 6 | |
| VLM evaluation | SEEDBench | BD-S Score12.88 | 6 | |
| Multimodal Perception | SEEDBench | Score77.32 | 4 | |
| General image understanding | SEEDBench | Score72.67 | 4 | |
| General Visual Question Answering | SEEDBench | Accuracy76.17 | 3 |
Showing 25 of 26 rows