Image Description on Our Benchmark
23.64METEORBrReMark
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| BrReMarkModel Category=Thinking with Images2026.06 | 23.64 | 21.57 | 47.68 | |
| BrReMark w/o rfmtModel Category=Thinking with Images2026.06 | 23.57 | 21.48 | 42.91 | |
| BrReMark w/o rlocModel Category=Thinking with Images2026.06 | 23.38 | 23.04 | 45.65 | |
| BrReMark w/o synthesisModel Category=Thinking with Images2026.06 | 23.16 | 23.44 | 42.46 | |
| BrReMark w/o rllmModel Category=Thinking with Images2026.06 | 22.31 | 21.6 | 45.69 | |
| Lingshu-32BModel Category=Medical Domain2026.06 | 22.21 | 23.57 | 46.33 | |
| LLaVA-v1.5-13BModel Category=General Domain2026.06 | 21.88 | 14.84 | 20.69 | |
| InternVL3.5-8BModel Category=General Domain2026.06 | 20.52 | 14.86 | 30.95 | |
| GRITModel Category=Thinking with Images2026.06 | 19.66 | 20.8 | 25.69 | |
| HuatuoGPT-V-7BModel Category=Medical Domain2026.06 | 19.55 | 16 | 22.99 | |
| MedVLM-R1Model Category=Medical Domain2026.06 | 19.51 | 12.63 | 18.74 | |
| Qwen2.5-VL-72BModel Category=General Domain2026.06 | 19.3 | 19.84 | 44.74 | |
| Qwen2.5-VL-7BModel Category=General Domain2026.06 | 18.67 | 18.18 | 41.83 | |
| Lingshu-7BModel Category=Medical Domain2026.06 | 17.06 | 21.47 | 42.72 |