paper-with-me

Spatial Reasoning 벤치마크

Spatial Reasoning on EmbSpatial-Bench

10개 결과 · ⬇ CSV · JSON

Generation

23.54 35.38 47.21 59.04 70.88 2023-03 2026-11 GPT-4V — 36.07 (2023-03-15) GPT-4V — 36.07 (2023-03-15) LLaVA-1.6 — 35.19 (2023-04-17) LLaVA-1.6 — 35.19 (2023-04-17) MiniGPT4 — 23.54 (2023-04-20) MiniGPT4 — 23.54 (2023-04-20) Qwen-VL-Max — 49.11 (2023-08-24) Qwen-VL-Max — 49.11 (2023-08-24) SoFar — 70.88 (2025-02-18) SoFar — 70.88 (2025-02-18) GPT-4V — 36.07 (2023-03-15) Qwen-VL-Max — 49.11 (2023-08-24) SoFar — 70.88 (2025-02-18)
RankModel Generation PaperCodeYear
1 SoFar 70.88 SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation qizekun/SoFar · zhangwenyao1/open6dor_v2_execution 2025
2 Qwen-VL-Max 49.11 Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond qwenlm/qwen-vl · brandon3964/multimodal-task-vector 2023
3 GPT-4V 36.07 GPT-4 Technical Report openai/evals · shmsw25/factscore · unispac/visual-adversarial-examples-jailbreak-large-language-models · +8 2023
4 LLaVA-1.6 35.19 Visual Instruction Tuning huggingface/transformers · haotian-liu/LLaVA · LLaVA-VL/LLaVA-NeXT · +10 2023
5 MiniGPT4 23.54 MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models vision-cair/minigpt-4 · zyang1580/binllm · 2024-MindSpore-1/Code6 · +3 2023
6 SoFar 70.88 SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation qizekun/SoFar · zhangwenyao1/open6dor_v2_execution 2025
7 Qwen-VL-Max 49.11 Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond qwenlm/qwen-vl · brandon3964/multimodal-task-vector 2023
8 GPT-4V 36.07 GPT-4 Technical Report openai/evals · shmsw25/factscore · unispac/visual-adversarial-examples-jailbreak-large-language-models · +8 2023
9 LLaVA-1.6 35.19 Visual Instruction Tuning huggingface/transformers · haotian-liu/LLaVA · LLaVA-VL/LLaVA-NeXT · +10 2023
10 MiniGPT4 23.54 MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models vision-cair/minigpt-4 · zyang1580/binllm · 2024-MindSpore-1/Code6 · +3 2023
1–10 / 10 페이지당 10 20 50 100