Reasoning Segmentation on ReasonSeg-SGDR v1.0 (test)
56.8Discriminative gIoURea2Seg
Evaluation results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| Rea2SegModel=Qwen2.5-VL-3B, Reranking Strategy=Top 32026.06 | 56.8 | 59.4 | 78.6 | 56 | 67.6 | 62.1 | 55 | 43.4 | 64.5 | 55.2 | |
| Rea2SegModel=LLaVA-v1.5-7B, Reranking Strategy=Top 32026.06 | 51.9 | 62.3 | 64.9 | 53.7 | 65.6 | 57.7 | 51.1 | 40.7 | 58.4 | 53.6 | |
| GPT-5-miniModel=Qwen2.5-VL-3B2026.06 | 51.9 | 60.2 | 68.3 | 29.8 | 54.7 | 35.9 | 43.7 | 21.7 | 54.7 | 36.9 | |
| Rea2SegModel=Qwen2.5-VL-3B, Reranking Strategy=Top 12026.06 | 48.9 | 48.8 | 73.1 | 61.8 | 58.8 | 49.8 | 45.4 | 32.2 | 56.6 | 48.2 | |
| LENS-CoTModel=Qwen2.5-VL-3B2026.06 | 45.9 | 34.5 | 46.7 | 30.8 | 49.3 | 39.8 | 40.8 | 24 | 45.7 | 32.3 | |
| Seg-ZeroModel=Qwen2.5-VL-7B2026.06 | 45.5 | 44 | 44 | 48.2 | 62 | 51.3 | 51.6 | 42.2 | 50.7 | 46.4 | |
| Rea2SegModel=LLaVA-v1.5-7B, Reranking Strategy=Top 12026.06 | 44.5 | 56.1 | 60 | 49.9 | 56.4 | 48.8 | 41.6 | 28.7 | 50.6 | 45.9 | |
| VisionReasonerModel=Qwen2.5-VL-7B2026.06 | 43.8 | 43.3 | 32.7 | 33.3 | 47.8 | 43.4 | 42.9 | 36.9 | 41.8 | 39.2 | |
| CoReSModel=LLaVA-v0-7B2026.06 | 34.3 | 39 | 25.3 | 17.9 | 38.6 | 28.9 | 34.4 | 22.4 | 33.2 | 27.1 | |
| READModel=LLaVA-v1.5-7B2026.06 | 27.6 | 15.2 | 29.3 | 22.7 | 46.5 | 36.9 | 34.8 | 21.3 | 34.6 | 24 | |
| LISAModel=LLaVA-v1-7B2026.06 | 26.9 | 16.9 | 25.1 | 19.3 | 28.4 | 24.1 | 28.4 | 19.2 | 27.2 | 19.9 | |
| SESAMEModel=LLaVA-v1.5-7B2026.06 | 21.7 | 7.3 | 25.5 | 21.9 | 36 | 28.6 | 33.3 | 18.7 | 29.1 | 19.1 |