Multimodal Reasoning on MME RWLite
52.6ScoreERGO
Evaluation Results
| Method | Links | |
|---|---|---|
| ERGOPixel Constraint=1280x28x28, Post-training Category=Efficiency-oriented Post Training Methods2025.09 | 52.6 | |
| PixelReasonerPixel Constraint=1280x28x28, Post-training Category=Non-efficiency-oriented Post Training Methods2025.09 | 49.8 | |
| ERGOPixel Constraint=640x28x28, Post-training Category=Efficiency-oriented Post Training Methods2025.09 | 49.6 | |
| VisionThinkPixel Constraint=1280x28x28, Post-training Category=Efficiency-oriented Post Training Methods, Inference Pipeline=inference with original pipeline2025.09 | 49 | |
| DeepEyesPixel Constraint=1280x28x28, Post-training Category=Non-efficiency-oriented Post Training Methods2025.09 | 48.9 | |
| DeepEyesPixel Constraint=640x28x28, Post-training Category=Non-efficiency-oriented Post Training Methods2025.09 | 48.9 | |
| PixelReasonerPixel Constraint=640x28x28, Post-training Category=Non-efficiency-oriented Post Training Methods2025.09 | 47.7 | |
| TreeVGRPixel Constraint=1280x28x28, Post-training Category=Non-efficiency-oriented Post Training Methods, Inference Pipeline=inference with original pipeline2025.09 | 47.5 | |
| TreeVGRPixel Constraint=640x28x28, Post-training Category=Non-efficiency-oriented Post Training Methods, Inference Pipeline=inference with original pipeline2025.09 | 47.5 | |
| Qwen2.5-VL-7B-Inst.Pixel Constraint=16384x28x282025.09 | 46.7 | |
| VisionThinkPixel Constraint=640x28x28, Post-training Category=Efficiency-oriented Post Training Methods, Inference Pipeline=inference with original pipeline2025.09 | 46.6 | |
| MGPOPixel Constraint=1280x28x28, Post-training Category=Efficiency-oriented Post Training Methods, Inference Pipeline=reproduction with their code using our data2025.09 | 44.4 | |
| MGPOPixel Constraint=640x28x28, Post-training Category=Efficiency-oriented Post Training Methods, Inference Pipeline=reproduction with their code using our data2025.09 | 44.4 | |
| Qwen2.5-VL-7B-Inst.Pixel Constraint=1280x28x282025.09 | 42.6 | |
| Qwen2.5-VL-7B-Inst.Pixel Constraint=640x28x282025.09 | 40.3 | |
| MiniO3Pixel Constraint=1280x28x28, Post-training Category=Non-efficiency-oriented Post Training Methods2025.09 | 36.7 | |
| MiniO3Pixel Constraint=640x28x28, Post-training Category=Non-efficiency-oriented Post Training Methods2025.09 | 34.4 |