MMBench
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Multimodal Understanding | MMBench | Accuracy90.6 | 637 | |
| Multimodal Model Evaluation | MMBench | Accuracy87.8 | 180 | |
| Multimodal Understanding | MMBench CN | Accuracy88.5 | 174 | |
| Multimodal Model Evaluation | MMBench Chinese | Accuracy82.6 | 154 | |
| Multimodal Understanding | MMBench (MMB) | Accuracy86.3 | 141 | |
| Vision Understanding | MMBench | Accuracy85 | 141 | |
| Multimodal Benchmarking | MMBench-CN | Score92.39 | 129 | |
| Multimodal Benchmarking | MMBench English | Accuracy70.4 | 125 | |
| Multimodal Evaluation | MMBench | MMB Score79.7 | 118 | |
| Multimodal Evaluation | MMBench CN | Accuracy74.3 | 83 | |
| Multimodal Benchmark | MMBench (MMB) | Accuracy81.8 | 81 | |
| Multimodal Reasoning | MMBench | Overall Score88.15 | 78 | |
| Visual Question Answering | MMBench (MMB) | Accuracy92.1 | 76 | |
| Multimodal Understanding | MMBench Chinese | MMB Benchmark (CN)89.5 | 70 | |
| GUI Grounding | MMBench-GUI L2 (test) | Average Error2.9 | 67 | |
| Multimodal Understanding | MMBench (test) | Accuracy84.2 | 67 | |
| Multi-modal Understanding | MMBench EN | Accuracy88.3 | 64 | |
| Multimodal Understanding | MMBench EN v1.1 | Accuracy89.5 | 63 | |
| Multimodal Benchmarking | MMBench (MMB) | MMB Score65.4 | 62 | |
| Multimodal Benchmarking | MMBench | Score83.4 | 62 | |
| Visual Question Answering | MMBench-CN | Accuracy93.13 | 62 | |
| Multimodal Benchmarking | MMBench | Accuracy84.4 | 58 | |
| Multimodal Understanding | MMBench (dev) | Accuracy80.41 | 58 | |
| Multi-modal Question Answering | MMBench | Accuracy86.4 | 55 | |
| Multi-modal Understanding | MMBench EN | Overall Score86.3 | 55 |
Showing 25 of 153 rows