General Perception on SEED
77AccuracyINTERNVL3-8B + PGT
Evaluation Results
| Method | Links | |
|---|---|---|
| INTERNVL3-8B + PGTBackbone=INTERNVL3-8B, Data=PGT-augmented2026.05 | 77 | |
| QWEN2.5-VL-7B + SPECIALIZED MIXBackbone=QWEN2.5-VL-7B, Data=Specialized Mix2026.05 | 76.6 | |
| INTERNVL3-8BBackbone=INTERNVL3-8B2026.05 | 76.4 | |
| QWEN2.5-VL-7BBackbone=QWEN2.5-VL-7B2026.05 | 76.4 | |
| QWEN2.5-VL-7B + PGTBackbone=QWEN2.5-VL-7B, Data=PGT-augmented2026.05 | 76.4 | |
| IMAGE JIGSAWMethod=IMAGE JIGSAW2026.05 | 75.9 | |
| QWEN2.5-VL-3B + SPECIALIZED MIXBackbone=QWEN2.5-VL-3B, Data=Specialized Mix2026.05 | 74.4 | |
| QWEN2.5-VL-3B + PGTBackbone=QWEN2.5-VL-3B, Data=PGT-augmented2026.05 | 74.2 | |
| QWEN2.5-VL-3BBackbone=QWEN2.5-VL-3B2026.05 | 73.7 | |
| SPATIAL-LADDER-3BMethod=SPATIAL-LADDER-3B2026.05 | 68.2 | |
| LLAVA-NEXT-LLAMA3-8BBackbone=LLAVA-NEXT-LLAMA3-8B2026.05 | 68.1 | |
| LLAVA-NEXT-LLAMA3-8B + PGTBackbone=LLAVA-NEXT-LLAMA3-8B, Data=PGT-augmented2026.05 | 67.2 | |
| LLAVA-NEXT-7B + PGTBackbone=LLAVA-NEXT-7B, Data=PGT-augmented2026.05 | 64.3 | |
| THINKLITE-VLMethod=THINKLITE-VL2026.05 | 64.3 | |
| LLAVA-NEXT-7BBackbone=LLAVA-NEXT-7B2026.05 | 63.4 |