Share your thoughts, 1 month free Claude Pro on usSee more

3D Sorting on 3D Sorting

92.4mIoU

Qwen3-8B (Ours)

Updated 25d ago

Evaluation Results

Method	Links
Qwen3-8B (Ours) 2026.03		92.4	0.145	100	0.51
Qwen2.5-7B (Ours) 2026.03		87.9	0.179	100	0.627
Cosmos-7B (Ours) 2026.03		87.5	0.234	100	0.592
Qwen3 (Vanilla GRPO) 2026.03		85	0.274	95.4	0.684
Qwen2.5-VL-7B (Ours) 2026.03		79.8	0.228	96.1	0.613
LayoutGPT (Gemini-2.5) 2026.03		78.1	0.471	98.2	0.709
Deepseek-R1 2026.03		77.6	0.566	90.3	0.783
LayoutGPT (Qwen3-235B) 2026.03		76.3	0.518	97.1	0.91
Gemini 2.5 Flash 2026.03		74.6	0.458	96.8	1.84
Cosmos-7B (Vanilla GRPO) 2026.03		72.9	0.297	93.7	0.811
Gemini 2.5 Pro 2026.03		72.4	0.593	97.6	2.18
Qwen2.5-VL-7B (CoT-SFT) 2026.03		71.3	0.33	84.7	0.853
Qwen2.5-7B (CoT-SFT) 2026.03		71.2	0.345	89.8	0.992
Qwen3-235B-Thinking 2026.03		70.8	0.856	95.7	2.208
Qwen3-VL-235B-Thinking 2026.03		70.6	0.568	91.8	1.9
Cosmos-7B (CoT-SFT) 2026.03		64.1	0.41	75.7	1.383
Qwen3-8B (CoT-SFT) 2026.03		63.5	0.513	85.4	1.61
Qwen2.5-7B (Ans-SFT) 2026.03		62.2	0.348	74.5	1.175
Deepseek-R1-0528 2026.03		60.1	1.163	79.9	2.021
Qwen2.5-VL-7B (Ans-SFT) 2026.03		57	0.423	69.8	0.9
Qwen3-8B (Ans-SFT) 2026.03		55.2	0.493	70	1.13
Cosmos-7B (Ans-SFT) 2026.03		50.1	0.577	68.3	1.794
Deepseek-V3 2026.03		23.6	1.242	62	2.01
Qwen3-VL-235B-Instruct 2026.03		14.5	2.323	42.1	8.12
Qwen3-235B-Instruct 2026.03		12.2	2.702	54.8	6.285