{"task":"Spatial Reasoning","dataset":"EmbSpatial-Bench","metric_names":["Generation"],"rows":[{"id":26530,"task":"Spatial Reasoning","parent_task":"Visual Question Answering","dataset":"EmbSpatial-Bench","model_name":"SoFar","metrics":{"Generation":"70.88"},"paper_url":"https://arxiv.org/abs/2502.13143v1","paper_title":"SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation","paper_date":"2025-02-18","code_links":[{"title":"qizekun/SoFar","url":"https://github.com/qizekun/SoFar"},{"title":"zhangwenyao1/open6dor_v2_execution","url":"https://github.com/zhangwenyao1/open6dor_v2_execution"}],"metrics_order":"[\"Generation\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":26531,"task":"Spatial Reasoning","parent_task":"Visual Question Answering","dataset":"EmbSpatial-Bench","model_name":"Qwen-VL-Max","metrics":{"Generation":"49.11"},"paper_url":"https://arxiv.org/abs/2308.12966v3","paper_title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","paper_date":"2023-08-24","code_links":[{"title":"qwenlm/qwen-vl","url":"https://github.com/qwenlm/qwen-vl"},{"title":"brandon3964/multimodal-task-vector","url":"https://github.com/brandon3964/multimodal-task-vector"}],"metrics_order":"[\"Generation\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":26532,"task":"Spatial Reasoning","parent_task":"Visual Question Answering","dataset":"EmbSpatial-Bench","model_name":"GPT-4V","metrics":{"Generation":"36.07"},"paper_url":"https://arxiv.org/abs/2303.08774v5","paper_title":"GPT-4 Technical Report","paper_date":"2023-03-15","code_links":[{"title":"openai/evals","url":"https://github.com/openai/evals"},{"title":"shmsw25/factscore","url":"https://github.com/shmsw25/factscore"},{"title":"unispac/visual-adversarial-examples-jailbreak-large-language-models","url":"https://github.com/unispac/visual-adversarial-examples-jailbreak-large-language-models"},{"title":"gpt4life/alpagasus","url":"https://github.com/gpt4life/alpagasus"},{"title":"emrgnt-cmplxty/zero-shot-replication","url":"https://github.com/emrgnt-cmplxty/zero-shot-replication"},{"title":"ethz-privsec/superhuman-ai-consistency","url":"https://github.com/ethz-privsec/superhuman-ai-consistency"},{"title":"ethz-spylab/superhuman-ai-consistency","url":"https://github.com/ethz-spylab/superhuman-ai-consistency"},{"title":"eternityyw/tram-benchmark","url":"https://github.com/eternityyw/tram-benchmark"},{"title":"AUCOHL/RTL-Repo","url":"https://github.com/AUCOHL/RTL-Repo"},{"title":"zach-zhiling-zheng/reticular_chemist","url":"https://github.com/zach-zhiling-zheng/reticular_chemist"},{"title":"lflage/openfactscore","url":"https://github.com/lflage/openfactscore"}],"metrics_order":"[\"Generation\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":26533,"task":"Spatial Reasoning","parent_task":"Visual Question Answering","dataset":"EmbSpatial-Bench","model_name":"LLaVA-1.6","metrics":{"Generation":"35.19"},"paper_url":"https://arxiv.org/abs/2304.08485v2","paper_title":"Visual Instruction Tuning","paper_date":"2023-04-17","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"haotian-liu/LLaVA","url":"https://github.com/haotian-liu/LLaVA"},{"title":"LLaVA-VL/LLaVA-NeXT","url":"https://github.com/LLaVA-VL/LLaVA-NeXT"},{"title":"computer-vision-in-the-wild/cvinw_readings","url":"https://github.com/computer-vision-in-the-wild/cvinw_readings"},{"title":"skunkworksai/bakllava","url":"https://github.com/skunkworksai/bakllava"},{"title":"tabtoyou/kollava","url":"https://github.com/tabtoyou/kollava"},{"title":"camenduru/llava-colab","url":"https://github.com/camenduru/llava-colab"},{"title":"sshh12/multi_token","url":"https://github.com/sshh12/multi_token"},{"title":"sunsmarterjie/chatterbox","url":"https://github.com/sunsmarterjie/chatterbox"},{"title":"ZhangYiqun018/StickerConv","url":"https://github.com/ZhangYiqun018/StickerConv"},{"title":"llava-annonymous/llava","url":"https://github.com/llava-annonymous/llava"},{"title":"qiujihao19/artemis","url":"https://github.com/qiujihao19/artemis"},{"title":"dinhvietcuong1996/icme25-inova","url":"https://github.com/dinhvietcuong1996/icme25-inova"}],"metrics_order":"[\"Generation\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":26534,"task":"Spatial Reasoning","parent_task":"Visual Question Answering","dataset":"EmbSpatial-Bench","model_name":"MiniGPT4","metrics":{"Generation":"23.54"},"paper_url":"https://arxiv.org/abs/2304.10592v2","paper_title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","paper_date":"2023-04-20","code_links":[{"title":"vision-cair/minigpt-4","url":"https://github.com/vision-cair/minigpt-4"},{"title":"zyang1580/binllm","url":"https://github.com/zyang1580/binllm"},{"title":"2024-MindSpore-1/Code6","url":"https://github.com/2024-MindSpore-1/Code6/tree/main/advanced_east"},{"title":"2024-MindSpore-1/Code5","url":"https://github.com/2024-MindSpore-1/Code5/tree/main/advanced_east"},{"title":"2023-MindSpore-1/ms-code-224","url":"https://github.com/2023-MindSpore-1/ms-code-224/tree/main/advanced_east"},{"title":"2023-MindSpore-1/ms-code-16","url":"https://github.com/2023-MindSpore-1/ms-code-16/tree/main/advanced_east"}],"metrics_order":"[\"Generation\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":143259,"task":"Spatial Reasoning","parent_task":"Visual Question Answering","dataset":"EmbSpatial-Bench","model_name":"SoFar","metrics":{"Generation":"70.88"},"paper_url":"https://arxiv.org/abs/2502.13143v1","paper_title":"SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation","paper_date":"2025-02-18","code_links":[{"title":"qizekun/SoFar","url":"https://github.com/qizekun/SoFar"},{"title":"zhangwenyao1/open6dor_v2_execution","url":"https://github.com/zhangwenyao1/open6dor_v2_execution"}],"metrics_order":"[\"Generation\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":143260,"task":"Spatial Reasoning","parent_task":"Visual Question Answering","dataset":"EmbSpatial-Bench","model_name":"Qwen-VL-Max","metrics":{"Generation":"49.11"},"paper_url":"https://arxiv.org/abs/2308.12966v3","paper_title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","paper_date":"2023-08-24","code_links":[{"title":"qwenlm/qwen-vl","url":"https://github.com/qwenlm/qwen-vl"},{"title":"brandon3964/multimodal-task-vector","url":"https://github.com/brandon3964/multimodal-task-vector"}],"metrics_order":"[\"Generation\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":143261,"task":"Spatial Reasoning","parent_task":"Visual Question Answering","dataset":"EmbSpatial-Bench","model_name":"GPT-4V","metrics":{"Generation":"36.07"},"paper_url":"https://arxiv.org/abs/2303.08774v5","paper_title":"GPT-4 Technical Report","paper_date":"2023-03-15","code_links":[{"title":"openai/evals","url":"https://github.com/openai/evals"},{"title":"shmsw25/factscore","url":"https://github.com/shmsw25/factscore"},{"title":"unispac/visual-adversarial-examples-jailbreak-large-language-models","url":"https://github.com/unispac/visual-adversarial-examples-jailbreak-large-language-models"},{"title":"gpt4life/alpagasus","url":"https://github.com/gpt4life/alpagasus"},{"title":"emrgnt-cmplxty/zero-shot-replication","url":"https://github.com/emrgnt-cmplxty/zero-shot-replication"},{"title":"ethz-privsec/superhuman-ai-consistency","url":"https://github.com/ethz-privsec/superhuman-ai-consistency"},{"title":"ethz-spylab/superhuman-ai-consistency","url":"https://github.com/ethz-spylab/superhuman-ai-consistency"},{"title":"eternityyw/tram-benchmark","url":"https://github.com/eternityyw/tram-benchmark"},{"title":"AUCOHL/RTL-Repo","url":"https://github.com/AUCOHL/RTL-Repo"},{"title":"zach-zhiling-zheng/reticular_chemist","url":"https://github.com/zach-zhiling-zheng/reticular_chemist"},{"title":"lflage/openfactscore","url":"https://github.com/lflage/openfactscore"}],"metrics_order":"[\"Generation\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":143262,"task":"Spatial Reasoning","parent_task":"Visual Question Answering","dataset":"EmbSpatial-Bench","model_name":"LLaVA-1.6","metrics":{"Generation":"35.19"},"paper_url":"https://arxiv.org/abs/2304.08485v2","paper_title":"Visual Instruction Tuning","paper_date":"2023-04-17","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"haotian-liu/LLaVA","url":"https://github.com/haotian-liu/LLaVA"},{"title":"LLaVA-VL/LLaVA-NeXT","url":"https://github.com/LLaVA-VL/LLaVA-NeXT"},{"title":"computer-vision-in-the-wild/cvinw_readings","url":"https://github.com/computer-vision-in-the-wild/cvinw_readings"},{"title":"skunkworksai/bakllava","url":"https://github.com/skunkworksai/bakllava"},{"title":"tabtoyou/kollava","url":"https://github.com/tabtoyou/kollava"},{"title":"camenduru/llava-colab","url":"https://github.com/camenduru/llava-colab"},{"title":"sshh12/multi_token","url":"https://github.com/sshh12/multi_token"},{"title":"sunsmarterjie/chatterbox","url":"https://github.com/sunsmarterjie/chatterbox"},{"title":"ZhangYiqun018/StickerConv","url":"https://github.com/ZhangYiqun018/StickerConv"},{"title":"llava-annonymous/llava","url":"https://github.com/llava-annonymous/llava"},{"title":"qiujihao19/artemis","url":"https://github.com/qiujihao19/artemis"},{"title":"dinhvietcuong1996/icme25-inova","url":"https://github.com/dinhvietcuong1996/icme25-inova"}],"metrics_order":"[\"Generation\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":143263,"task":"Spatial Reasoning","parent_task":"Visual Question Answering","dataset":"EmbSpatial-Bench","model_name":"MiniGPT4","metrics":{"Generation":"23.54"},"paper_url":"https://arxiv.org/abs/2304.10592v2","paper_title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","paper_date":"2023-04-20","code_links":[{"title":"vision-cair/minigpt-4","url":"https://github.com/vision-cair/minigpt-4"},{"title":"zyang1580/binllm","url":"https://github.com/zyang1580/binllm"},{"title":"2024-MindSpore-1/Code6","url":"https://github.com/2024-MindSpore-1/Code6/tree/main/advanced_east"},{"title":"2024-MindSpore-1/Code5","url":"https://github.com/2024-MindSpore-1/Code5/tree/main/advanced_east"},{"title":"2023-MindSpore-1/ms-code-224","url":"https://github.com/2023-MindSpore-1/ms-code-224/tree/main/advanced_east"},{"title":"2023-MindSpore-1/ms-code-16","url":"https://github.com/2023-MindSpore-1/ms-code-16/tree/main/advanced_east"}],"metrics_order":"[\"Generation\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]}]}