SpectrumLeaderboard / leaderboard_v_1.0.json
little1d's picture
Upload 4 files
538877b verified
{
"leaderboard_info": {
"total_models": 18
},
"models": [
{
"name": "Claude-3.7-Sonnet",
"name_link": "https://www.anthropic.com/claude",
"submitter": "Anthropic Team",
"submitter_link": "mailto:support@anthropic.com",
"submission_time": "2025-08-01T17:09:29.917540Z",
"model_type": "proprietary",
"model_size": "Unknown",
"is_multimodal": true,
"results": {
"Signal": {
"accuracy": 75.78,
"subcategories": {
"Spectrum Type Classification": {
"accuracy": 96.36
},
"Spectrum Quality Assessment": {
"accuracy": 38.33
},
"Basic Feature Extraction": {
"accuracy": 86.27
},
"Impurity Peak Detection": {
"accuracy": 82.14
}
}
},
"Perception": {
"accuracy": 79.9,
"subcategories": {
"Functional Group Recognition": {
"accuracy": 71.43
},
"Elemental Compositional Prediction": {
"accuracy": 88.89
},
"Peak Assignment": {
"accuracy": 71.05
},
"Basic Property Prediction": {
"accuracy": 88.24
}
}
},
"Semantic": {
"accuracy": 81.94,
"subcategories": {
"Molecular Structure Elucidation": {
"accuracy": 82.28
},
"Fusing Spectroscopic Modalities": {
"accuracy": 74.36
},
"Multimodal Molecular Reasoning": {
"accuracy": 89.19
}
}
},
"Generation": {
"accuracy": 8.42,
"subcategories": {
"Forward Problems": {
"accuracy": 20.0
},
"Inverse Problems": {
"accuracy": 0
},
"De Novo Generation": {
"accuracy": 5.26
}
}
},
"overall_accuracy": 61.51
},
"model_info": {
"homepage": "https://www.anthropic.com/claude",
"paper": "",
"code": "",
"description": "Claude 3.7 Sonnet with enhanced multimodal capabilities"
}
},
{
"name": "Doubao-1.5-Vision-Pro-Thinking",
"name_link": "https://www.volcengine.com/product/doubao",
"submitter": "ByteDance Team",
"submitter_link": "https://www.volcengine.com/",
"submission_time": "2025-08-01T17:09:29.934647Z",
"model_type": "proprietary",
"model_size": "Unknown",
"is_multimodal": true,
"results": {
"Signal": {
"accuracy": 69.41,
"subcategories": {
"Spectrum Type Classification": {
"accuracy": 96.36
},
"Spectrum Quality Assessment": {
"accuracy": 35.0
},
"Basic Feature Extraction": {
"accuracy": 78.43
},
"Impurity Peak Detection": {
"accuracy": 67.86
}
}
},
"Perception": {
"accuracy": 74.69,
"subcategories": {
"Functional Group Recognition": {
"accuracy": 53.33
},
"Elemental Compositional Prediction": {
"accuracy": 80.56
},
"Peak Assignment": {
"accuracy": 73.68
},
"Basic Property Prediction": {
"accuracy": 91.18
}
}
},
"Semantic": {
"accuracy": 75.77,
"subcategories": {
"Molecular Structure Elucidation": {
"accuracy": 68.75
},
"Fusing Spectroscopic Modalities": {
"accuracy": 66.67
},
"Multimodal Molecular Reasoning": {
"accuracy": 91.89
}
}
},
"Generation": {
"accuracy": 25.64,
"subcategories": {
"Forward Problems": {
"accuracy": 66.67
},
"Inverse Problems": {
"accuracy": 5.0
},
"De Novo Generation": {
"accuracy": 5.26
}
}
},
"overall_accuracy": 61.38
},
"model_info": {
"homepage": "https://www.volcengine.com/product/doubao",
"paper": "",
"code": "",
"description": "Doubao 1.5 Vision Pro with enhanced reasoning capabilities"
}
},
{
"name": "Qwen2.5-VL-72B-Instruct",
"name_link": "https://qwenlm.github.io/",
"submitter": "Alibaba DAMO Academy",
"submitter_link": "https://damo.alibaba.com/",
"submission_time": "2025-08-01T17:09:29.925741Z",
"model_type": "open_source",
"model_size": "72B",
"is_multimodal": true,
"results": {
"Signal": {
"accuracy": 78.0,
"subcategories": {
"Spectrum Type Classification": {
"accuracy": 94.55
},
"Spectrum Quality Assessment": {
"accuracy": 38.33
},
"Basic Feature Extraction": {
"accuracy": 86.27
},
"Impurity Peak Detection": {
"accuracy": 92.86
}
}
},
"Perception": {
"accuracy": 72.49,
"subcategories": {
"Functional Group Recognition": {
"accuracy": 42.22
},
"Elemental Compositional Prediction": {
"accuracy": 80.56
},
"Peak Assignment": {
"accuracy": 78.95
},
"Basic Property Prediction": {
"accuracy": 88.24
}
}
},
"Semantic": {
"accuracy": 78.35,
"subcategories": {
"Molecular Structure Elucidation": {
"accuracy": 66.25
},
"Fusing Spectroscopic Modalities": {
"accuracy": 76.92
},
"Multimodal Molecular Reasoning": {
"accuracy": 91.89
}
}
},
"Generation": {
"accuracy": 13.51,
"subcategories": {
"Forward Problems": {
"accuracy": 30.0
},
"Inverse Problems": {
"accuracy": 0
},
"De Novo Generation": {
"accuracy": 10.53
}
}
},
"overall_accuracy": 60.59
},
"model_info": {
"homepage": "https://qwenlm.github.io/",
"paper": "https://arxiv.org/abs/2407.10671",
"code": "https://github.com/QwenLM/Qwen2.5",
"description": "Qwen2.5-VL-72B large-scale open-source vision-language model"
}
},
{
"name": "GPT-4.1",
"name_link": "https://openai.com/gpt-4",
"submitter": "OpenAI Team",
"submitter_link": "mailto:research@openai.com",
"submission_time": "2025-08-01T17:09:29.920918Z",
"model_type": "proprietary",
"model_size": "Unknown",
"is_multimodal": true,
"results": {
"Signal": {
"accuracy": 73.72,
"subcategories": {
"Spectrum Type Classification": {
"accuracy": 94.55
},
"Spectrum Quality Assessment": {
"accuracy": 28.33
},
"Basic Feature Extraction": {
"accuracy": 86.27
},
"Impurity Peak Detection": {
"accuracy": 85.71
}
}
},
"Perception": {
"accuracy": 68.42,
"subcategories": {
"Functional Group Recognition": {
"accuracy": 53.33
},
"Elemental Compositional Prediction": {
"accuracy": 77.78
},
"Peak Assignment": {
"accuracy": 63.16
},
"Basic Property Prediction": {
"accuracy": 79.41
}
}
},
"Semantic": {
"accuracy": 80.35,
"subcategories": {
"Molecular Structure Elucidation": {
"accuracy": 82.5
},
"Fusing Spectroscopic Modalities": {
"accuracy": 66.67
},
"Multimodal Molecular Reasoning": {
"accuracy": 91.89
}
}
},
"Generation": {
"accuracy": 14.62,
"subcategories": {
"Forward Problems": {
"accuracy": 33.33
},
"Inverse Problems": {
"accuracy": 10.53
},
"De Novo Generation": {
"accuracy": 0
}
}
},
"overall_accuracy": 59.28
},
"model_info": {
"homepage": "https://openai.com/gpt-4",
"paper": "https://arxiv.org/abs/2303.08774",
"code": "",
"description": "GPT-4.1 with improved reasoning capabilities"
}
},
{
"name": "Qwen-VL-Max",
"name_link": "https://qwenlm.github.io/",
"submitter": "Alibaba DAMO Academy",
"submitter_link": "https://damo.alibaba.com/",
"submission_time": "2025-08-01T17:09:29.923747Z",
"model_type": "proprietary",
"model_size": "Unknown",
"is_multimodal": true,
"results": {
"Signal": {
"accuracy": 78.57,
"subcategories": {
"Spectrum Type Classification": {
"accuracy": 94.55
},
"Spectrum Quality Assessment": {
"accuracy": 36.67
},
"Basic Feature Extraction": {
"accuracy": 90.2
},
"Impurity Peak Detection": {
"accuracy": 92.86
}
}
},
"Perception": {
"accuracy": 76.94,
"subcategories": {
"Functional Group Recognition": {
"accuracy": 60.0
},
"Elemental Compositional Prediction": {
"accuracy": 80.56
},
"Peak Assignment": {
"accuracy": 78.95
},
"Basic Property Prediction": {
"accuracy": 88.24
}
}
},
"Semantic": {
"accuracy": 65.39,
"subcategories": {
"Molecular Structure Elucidation": {
"accuracy": 32.5
},
"Fusing Spectroscopic Modalities": {
"accuracy": 71.79
},
"Multimodal Molecular Reasoning": {
"accuracy": 91.89
}
}
},
"Generation": {
"accuracy": 16.2,
"subcategories": {
"Forward Problems": {
"accuracy": 43.33
},
"Inverse Problems": {
"accuracy": 0
},
"De Novo Generation": {
"accuracy": 5.26
}
}
},
"overall_accuracy": 59.27
},
"model_info": {
"homepage": "https://qwenlm.github.io/",
"paper": "https://arxiv.org/abs/2308.12966",
"code": "https://github.com/QwenLM/Qwen-VL",
"description": "Qwen-VL-Max with advanced vision-language understanding"
}
},
{
"name": "GPT-4-Vision",
"name_link": "https://openai.com/gpt-4",
"submitter": "OpenAI Team",
"submitter_link": "mailto:research@openai.com",
"submission_time": "2025-08-01T17:09:29.921628Z",
"model_type": "proprietary",
"model_size": "Unknown",
"is_multimodal": true,
"results": {
"Signal": {
"accuracy": 73.32,
"subcategories": {
"Spectrum Type Classification": {
"accuracy": 94.55
},
"Spectrum Quality Assessment": {
"accuracy": 33.33
},
"Basic Feature Extraction": {
"accuracy": 72.55
},
"Impurity Peak Detection": {
"accuracy": 92.86
}
}
},
"Perception": {
"accuracy": 74.74,
"subcategories": {
"Functional Group Recognition": {
"accuracy": 73.33
},
"Elemental Compositional Prediction": {
"accuracy": 72.22
},
"Peak Assignment": {
"accuracy": 71.05
},
"Basic Property Prediction": {
"accuracy": 82.35
}
}
},
"Semantic": {
"accuracy": 74.97,
"subcategories": {
"Molecular Structure Elucidation": {
"accuracy": 73.75
},
"Fusing Spectroscopic Modalities": {
"accuracy": 53.85
},
"Multimodal Molecular Reasoning": {
"accuracy": 97.3
}
}
},
"Generation": {
"accuracy": 9.44,
"subcategories": {
"Forward Problems": {
"accuracy": 23.33
},
"Inverse Problems": {
"accuracy": 5.0
},
"De Novo Generation": {
"accuracy": 0
}
}
},
"overall_accuracy": 58.12
},
"model_info": {
"homepage": "https://openai.com/gpt-4",
"paper": "https://arxiv.org/abs/2303.08774",
"code": "",
"description": "GPT-4 with vision capabilities for multimodal understanding"
}
},
{
"name": "Claude-3.5-Sonnet",
"name_link": "https://www.anthropic.com/claude",
"submitter": "Anthropic Team",
"submitter_link": "mailto:support@anthropic.com",
"submission_time": "2025-08-01T17:09:29.916821Z",
"model_type": "proprietary",
"model_size": "Unknown",
"is_multimodal": true,
"results": {
"Signal": {
"accuracy": 68.15,
"subcategories": {
"Spectrum Type Classification": {
"accuracy": 96.36
},
"Spectrum Quality Assessment": {
"accuracy": 28.33
},
"Basic Feature Extraction": {
"accuracy": 76.47
},
"Impurity Peak Detection": {
"accuracy": 71.43
}
}
},
"Perception": {
"accuracy": 74.85,
"subcategories": {
"Functional Group Recognition": {
"accuracy": 60.0
},
"Elemental Compositional Prediction": {
"accuracy": 77.78
},
"Peak Assignment": {
"accuracy": 76.32
},
"Basic Property Prediction": {
"accuracy": 85.29
}
}
},
"Semantic": {
"accuracy": 82.11,
"subcategories": {
"Molecular Structure Elucidation": {
"accuracy": 82.5
},
"Fusing Spectroscopic Modalities": {
"accuracy": 69.23
},
"Multimodal Molecular Reasoning": {
"accuracy": 94.59
}
}
},
"Generation": {
"accuracy": 6.67,
"subcategories": {
"Forward Problems": {
"accuracy": 20.0
},
"Inverse Problems": {
"accuracy": 0
},
"De Novo Generation": {
"accuracy": 0
}
}
},
"overall_accuracy": 57.95
},
"model_info": {
"homepage": "https://www.anthropic.com/claude",
"paper": "",
"code": "",
"description": "Claude 3.5 Sonnet with advanced reasoning and multimodal capabilities"
}
},
{
"name": "Claude-4-Opus",
"name_link": "https://www.anthropic.com/claude",
"submitter": "Anthropic Team",
"submitter_link": "mailto:support@anthropic.com",
"submission_time": "2025-08-01T17:09:29.919719Z",
"model_type": "proprietary",
"model_size": "Unknown",
"is_multimodal": true,
"results": {
"Signal": {
"accuracy": 77.2,
"subcategories": {
"Spectrum Type Classification": {
"accuracy": 96.36
},
"Spectrum Quality Assessment": {
"accuracy": 33.33
},
"Basic Feature Extraction": {
"accuracy": 86.27
},
"Impurity Peak Detection": {
"accuracy": 92.86
}
}
},
"Perception": {
"accuracy": 78.25,
"subcategories": {
"Functional Group Recognition": {
"accuracy": 73.33
},
"Elemental Compositional Prediction": {
"accuracy": 83.33
},
"Peak Assignment": {
"accuracy": 71.05
},
"Basic Property Prediction": {
"accuracy": 85.29
}
}
},
"Semantic": {
"accuracy": 65.3,
"subcategories": {
"Molecular Structure Elucidation": {
"accuracy": 32.5
},
"Fusing Spectroscopic Modalities": {
"accuracy": 76.92
},
"Multimodal Molecular Reasoning": {
"accuracy": 86.49
}
}
},
"Generation": {
"accuracy": 7.31,
"subcategories": {
"Forward Problems": {
"accuracy": 16.67
},
"Inverse Problems": {
"accuracy": 0
},
"De Novo Generation": {
"accuracy": 5.26
}
}
},
"overall_accuracy": 57.02
},
"model_info": {
"homepage": "https://www.anthropic.com/claude",
"paper": "",
"code": "",
"description": "Claude 4 Opus - most capable model in the Claude family"
}
},
{
"name": "Doubao-1.5-Vision-Pro",
"name_link": "https://www.volcengine.com/product/doubao",
"submitter": "ByteDance Team",
"submitter_link": "https://www.volcengine.com/",
"submission_time": "2025-08-01T17:09:29.932862Z",
"model_type": "proprietary",
"model_size": "Unknown",
"is_multimodal": true,
"results": {
"Signal": {
"accuracy": 75.7,
"subcategories": {
"Spectrum Type Classification": {
"accuracy": 98.18
},
"Spectrum Quality Assessment": {
"accuracy": 33.33
},
"Basic Feature Extraction": {
"accuracy": 78.43
},
"Impurity Peak Detection": {
"accuracy": 92.86
}
}
},
"Perception": {
"accuracy": 76.66,
"subcategories": {
"Functional Group Recognition": {
"accuracy": 66.67
},
"Elemental Compositional Prediction": {
"accuracy": 83.33
},
"Peak Assignment": {
"accuracy": 68.42
},
"Basic Property Prediction": {
"accuracy": 88.24
}
}
},
"Semantic": {
"accuracy": 71.03,
"subcategories": {
"Molecular Structure Elucidation": {
"accuracy": 67.5
},
"Fusing Spectroscopic Modalities": {
"accuracy": 56.41
},
"Multimodal Molecular Reasoning": {
"accuracy": 89.19
}
}
},
"Generation": {
"accuracy": 2.22,
"subcategories": {
"Forward Problems": {
"accuracy": 6.67
},
"Inverse Problems": {
"accuracy": 0
},
"De Novo Generation": {
"accuracy": 0
}
}
},
"overall_accuracy": 56.4
},
"model_info": {
"homepage": "https://www.volcengine.com/product/doubao",
"paper": "",
"code": "",
"description": "Doubao 1.5 Vision Pro multimodal model"
}
},
{
"name": "InternVL3-78B",
"name_link": "https://internvl.github.io/",
"submitter": "Shanghai AI Laboratory",
"submitter_link": "https://www.shlab.org.cn/",
"submission_time": "2025-08-01T17:09:29.926853Z",
"model_type": "open_source",
"model_size": "78B",
"is_multimodal": true,
"results": {
"Signal": {
"accuracy": 69.18,
"subcategories": {
"Spectrum Type Classification": {
"accuracy": 96.36
},
"Spectrum Quality Assessment": {
"accuracy": 38.33
},
"Basic Feature Extraction": {
"accuracy": 70.59
},
"Impurity Peak Detection": {
"accuracy": 71.43
}
}
},
"Perception": {
"accuracy": 73.33,
"subcategories": {
"Functional Group Recognition": {
"accuracy": 48.49
},
"Elemental Compositional Prediction": {
"accuracy": 75.0
},
"Peak Assignment": {
"accuracy": 81.58
},
"Basic Property Prediction": {
"accuracy": 88.24
}
}
},
"Semantic": {
"accuracy": 71.84,
"subcategories": {
"Molecular Structure Elucidation": {
"accuracy": 62.5
},
"Fusing Spectroscopic Modalities": {
"accuracy": 69.23
},
"Multimodal Molecular Reasoning": {
"accuracy": 83.78
}
}
},
"Generation": {
"accuracy": 9.53,
"subcategories": {
"Forward Problems": {
"accuracy": 23.33
},
"Inverse Problems": {
"accuracy": 0
},
"De Novo Generation": {
"accuracy": 5.26
}
}
},
"overall_accuracy": 55.97
},
"model_info": {
"homepage": "https://internvl.github.io/",
"paper": "https://arxiv.org/abs/2312.14238",
"code": "https://github.com/OpenGVLab/InternVL",
"description": "InternVL3-78B large-scale multimodal foundation model"
}
},
{
"name": "GPT-4o",
"name_link": "https://openai.com/gpt-4",
"submitter": "OpenAI Team",
"submitter_link": "mailto:research@openai.com",
"submission_time": "2025-08-01T17:09:29.920289Z",
"model_type": "proprietary",
"model_size": "Unknown",
"is_multimodal": true,
"results": {
"Signal": {
"accuracy": 72.8,
"subcategories": {
"Spectrum Type Classification": {
"accuracy": 96.36
},
"Spectrum Quality Assessment": {
"accuracy": 33.33
},
"Basic Feature Extraction": {
"accuracy": 68.63
},
"Impurity Peak Detection": {
"accuracy": 92.86
}
}
},
"Perception": {
"accuracy": 69.53,
"subcategories": {
"Functional Group Recognition": {
"accuracy": 57.78
},
"Elemental Compositional Prediction": {
"accuracy": 77.78
},
"Peak Assignment": {
"accuracy": 63.16
},
"Basic Property Prediction": {
"accuracy": 79.41
}
}
},
"Semantic": {
"accuracy": 77.44,
"subcategories": {
"Molecular Structure Elucidation": {
"accuracy": 78.75
},
"Fusing Spectroscopic Modalities": {
"accuracy": 58.97
},
"Multimodal Molecular Reasoning": {
"accuracy": 94.59
}
}
},
"Generation": {
"accuracy": 3.33,
"subcategories": {
"Forward Problems": {
"accuracy": 10.0
},
"Inverse Problems": {
"accuracy": 0
},
"De Novo Generation": {
"accuracy": 0
}
}
},
"overall_accuracy": 55.77
},
"model_info": {
"homepage": "https://openai.com/gpt-4",
"paper": "https://arxiv.org/abs/2303.08774",
"code": "",
"description": "GPT-4o with enhanced multimodal capabilities"
}
},
{
"name": "Grok-2-Vision",
"name_link": "https://grok.x.ai/",
"submitter": "xAI Team",
"submitter_link": "mailto:team@x.ai",
"submission_time": "2025-08-01T17:09:29.922697Z",
"model_type": "proprietary",
"model_size": "Unknown",
"is_multimodal": true,
"results": {
"Signal": {
"accuracy": 72.5,
"subcategories": {
"Spectrum Type Classification": {
"accuracy": 94.55
},
"Spectrum Quality Assessment": {
"accuracy": 31.67
},
"Basic Feature Extraction": {
"accuracy": 74.51
},
"Impurity Peak Detection": {
"accuracy": 89.29
}
}
},
"Perception": {
"accuracy": 75.26,
"subcategories": {
"Functional Group Recognition": {
"accuracy": 64.44
},
"Elemental Compositional Prediction": {
"accuracy": 80.56
},
"Peak Assignment": {
"accuracy": 73.68
},
"Basic Property Prediction": {
"accuracy": 82.35
}
}
},
"Semantic": {
"accuracy": 61.75,
"subcategories": {
"Molecular Structure Elucidation": {
"accuracy": 37.5
},
"Fusing Spectroscopic Modalities": {
"accuracy": 66.67
},
"Multimodal Molecular Reasoning": {
"accuracy": 81.08
}
}
},
"Generation": {
"accuracy": 7.78,
"subcategories": {
"Forward Problems": {
"accuracy": 23.33
},
"Inverse Problems": {
"accuracy": 0
},
"De Novo Generation": {
"accuracy": 0
}
}
},
"overall_accuracy": 54.32
},
"model_info": {
"homepage": "https://grok.x.ai/",
"paper": "",
"code": "",
"description": "Grok-2 with vision capabilities for multimodal reasoning"
}
},
{
"name": "Claude-3.5-Haiku",
"name_link": "https://www.anthropic.com/claude",
"submitter": "Anthropic Team",
"submitter_link": "mailto:support@anthropic.com",
"submission_time": "2025-08-01T17:09:29.919136Z",
"model_type": "proprietary",
"model_size": "Unknown",
"is_multimodal": true,
"results": {
"Signal": {
"accuracy": 67.52,
"subcategories": {
"Spectrum Type Classification": {
"accuracy": 94.55
},
"Spectrum Quality Assessment": {
"accuracy": 31.67
},
"Basic Feature Extraction": {
"accuracy": 50.98
},
"Impurity Peak Detection": {
"accuracy": 92.86
}
}
},
"Perception": {
"accuracy": 73.61,
"subcategories": {
"Functional Group Recognition": {
"accuracy": 66.67
},
"Elemental Compositional Prediction": {
"accuracy": 75.0
},
"Peak Assignment": {
"accuracy": 76.32
},
"Basic Property Prediction": {
"accuracy": 76.47
}
}
},
"Semantic": {
"accuracy": 70.89,
"subcategories": {
"Molecular Structure Elucidation": {
"accuracy": 67.5
},
"Fusing Spectroscopic Modalities": {
"accuracy": 64.1
},
"Multimodal Molecular Reasoning": {
"accuracy": 81.08
}
}
},
"Generation": {
"accuracy": 3.33,
"subcategories": {
"Forward Problems": {
"accuracy": 10.0
},
"Inverse Problems": {
"accuracy": 0
},
"De Novo Generation": {
"accuracy": 0
}
}
},
"overall_accuracy": 53.84
},
"model_info": {
"homepage": "https://www.anthropic.com/claude",
"paper": "",
"code": "",
"description": "Claude 3.5 Haiku - fast and efficient multimodal model"
}
},
{
"name": "Claude-4-Sonnet",
"name_link": "https://www.anthropic.com/claude",
"submitter": "Anthropic Team",
"submitter_link": "mailto:support@anthropic.com",
"submission_time": "2025-08-01T17:09:29.918518Z",
"model_type": "proprietary",
"model_size": "Unknown",
"is_multimodal": true,
"results": {
"Signal": {
"accuracy": 78.11,
"subcategories": {
"Spectrum Type Classification": {
"accuracy": 96.36
},
"Spectrum Quality Assessment": {
"accuracy": 35.0
},
"Basic Feature Extraction": {
"accuracy": 88.24
},
"Impurity Peak Detection": {
"accuracy": 92.86
}
}
},
"Perception": {
"accuracy": 65.78,
"subcategories": {
"Functional Group Recognition": {
"accuracy": 62.22
},
"Elemental Compositional Prediction": {
"accuracy": 63.89
},
"Peak Assignment": {
"accuracy": 60.53
},
"Basic Property Prediction": {
"accuracy": 76.47
}
}
},
"Semantic": {
"accuracy": 41.57,
"subcategories": {
"Molecular Structure Elucidation": {
"accuracy": 16.25
},
"Fusing Spectroscopic Modalities": {
"accuracy": 43.59
},
"Multimodal Molecular Reasoning": {
"accuracy": 64.86
}
}
},
"Generation": {
"accuracy": 8.13,
"subcategories": {
"Forward Problems": {
"accuracy": 3.33
},
"Inverse Problems": {
"accuracy": 0
},
"De Novo Generation": {
"accuracy": 21.05
}
}
},
"overall_accuracy": 48.4
},
"model_info": {
"homepage": "https://www.anthropic.com/claude",
"paper": "",
"code": "",
"description": "Claude 4 Sonnet with advanced reasoning capabilities"
}
},
{
"name": "Qwen2.5-VL-32B-Instruct",
"name_link": "https://qwenlm.github.io/",
"submitter": "Alibaba DAMO Academy",
"submitter_link": "https://damo.alibaba.com/",
"submission_time": "2025-08-01T17:09:29.924718Z",
"model_type": "open_source",
"model_size": "32B",
"is_multimodal": true,
"results": {
"Signal": {
"accuracy": 57.02,
"subcategories": {
"Spectrum Type Classification": {
"accuracy": 92.73
},
"Spectrum Quality Assessment": {
"accuracy": 26.67
},
"Basic Feature Extraction": {
"accuracy": 37.25
},
"Impurity Peak Detection": {
"accuracy": 71.43
}
}
},
"Perception": {
"accuracy": 48.89,
"subcategories": {
"Functional Group Recognition": {
"accuracy": 57.78
},
"Elemental Compositional Prediction": {
"accuracy": 44.44
},
"Peak Assignment": {
"accuracy": 31.58
},
"Basic Property Prediction": {
"accuracy": 61.76
}
}
},
"Semantic": {
"accuracy": 17.03,
"subcategories": {
"Molecular Structure Elucidation": {
"accuracy": 0.0
},
"Fusing Spectroscopic Modalities": {
"accuracy": 5.13
},
"Multimodal Molecular Reasoning": {
"accuracy": 45.95
}
}
},
"Generation": {
"accuracy": 6.67,
"subcategories": {
"Forward Problems": {
"accuracy": 20.0
},
"Inverse Problems": {
"accuracy": 0
},
"De Novo Generation": {
"accuracy": 0
}
}
},
"overall_accuracy": 32.4
},
"model_info": {
"homepage": "https://qwenlm.github.io/",
"paper": "https://arxiv.org/abs/2407.10671",
"code": "https://github.com/QwenLM/Qwen2.5",
"description": "Qwen2.5-VL-32B open-source vision-language model"
}
},
{
"name": "DeepSeek-VL2",
"name_link": "https://www.deepseek.com/",
"submitter": "DeepSeek Team",
"submitter_link": "https://github.com/deepseek-ai",
"submission_time": "2025-08-01T17:09:29.931327Z",
"model_type": "open_source",
"model_size": "Unknown",
"is_multimodal": true,
"results": {
"Signal": {
"accuracy": 33.51,
"subcategories": {
"Spectrum Type Classification": {
"accuracy": 52.73
},
"Spectrum Quality Assessment": {
"accuracy": 23.33
},
"Basic Feature Extraction": {
"accuracy": 29.41
},
"Impurity Peak Detection": {
"accuracy": 28.57
}
}
},
"Perception": {
"accuracy": 28.91,
"subcategories": {
"Functional Group Recognition": {
"accuracy": 8.89
},
"Elemental Compositional Prediction": {
"accuracy": 27.78
},
"Peak Assignment": {
"accuracy": 28.95
},
"Basic Property Prediction": {
"accuracy": 50.0
}
}
},
"Semantic": {
"accuracy": 20.94,
"subcategories": {
"Molecular Structure Elucidation": {
"accuracy": 15.0
},
"Fusing Spectroscopic Modalities": {
"accuracy": 15.38
},
"Multimodal Molecular Reasoning": {
"accuracy": 32.43
}
}
},
"Generation": {
"accuracy": 6.75,
"subcategories": {
"Forward Problems": {
"accuracy": 10.0
},
"Inverse Problems": {
"accuracy": 5.0
},
"De Novo Generation": {
"accuracy": 5.26
}
}
},
"overall_accuracy": 22.53
},
"model_info": {
"homepage": "https://www.deepseek.com/",
"paper": "https://arxiv.org/abs/2412.10302",
"code": "https://github.com/deepseek-ai/DeepSeek-VL2",
"description": "DeepSeek-VL2 advanced vision-language model"
}
},
{
"name": "Llama-3.2-90B-Vision-Instruct",
"name_link": "https://llama.meta.com/",
"submitter": "Meta AI",
"submitter_link": "https://ai.meta.com/",
"submission_time": "2025-08-01T17:09:29.929751Z",
"model_type": "open_source",
"model_size": "90B",
"is_multimodal": true,
"results": {
"Signal": {
"accuracy": 27.12,
"subcategories": {
"Spectrum Type Classification": {
"accuracy": 38.18
},
"Spectrum Quality Assessment": {
"accuracy": 10.0
},
"Basic Feature Extraction": {
"accuracy": 35.29
},
"Impurity Peak Detection": {
"accuracy": 25.0
}
}
},
"Perception": {
"accuracy": 23.77,
"subcategories": {
"Functional Group Recognition": {
"accuracy": 17.78
},
"Elemental Compositional Prediction": {
"accuracy": 27.78
},
"Peak Assignment": {
"accuracy": 28.95
},
"Basic Property Prediction": {
"accuracy": 20.59
}
}
},
"Semantic": {
"accuracy": 23.21,
"subcategories": {
"Molecular Structure Elucidation": {
"accuracy": 21.25
},
"Fusing Spectroscopic Modalities": {
"accuracy": 5.13
},
"Multimodal Molecular Reasoning": {
"accuracy": 43.24
}
}
},
"Generation": {
"accuracy": 0,
"subcategories": {
"Forward Problems": {
"accuracy": 0
},
"Inverse Problems": {
"accuracy": 0
},
"De Novo Generation": {
"accuracy": 0
}
}
},
"overall_accuracy": 18.52
},
"model_info": {
"homepage": "https://llama.meta.com/",
"paper": "https://arxiv.org/abs/2407.21783",
"code": "https://github.com/meta-llama/llama3",
"description": "Llama 3.2 90B with vision capabilities"
}
},
{
"name": "Llama-3.2-11B-Vision-Instruct",
"name_link": "https://llama.meta.com/",
"submitter": "Meta AI",
"submitter_link": "https://ai.meta.com/",
"submission_time": "2025-08-01T17:09:29.928044Z",
"model_type": "open_source",
"model_size": "11B",
"is_multimodal": true,
"results": {
"Signal": {
"accuracy": 21.24,
"subcategories": {
"Spectrum Type Classification": {
"accuracy": 34.55
},
"Spectrum Quality Assessment": {
"accuracy": 11.67
},
"Basic Feature Extraction": {
"accuracy": 13.73
},
"Impurity Peak Detection": {
"accuracy": 25.0
}
}
},
"Perception": {
"accuracy": 26.72,
"subcategories": {
"Functional Group Recognition": {
"accuracy": 20.0
},
"Elemental Compositional Prediction": {
"accuracy": 41.67
},
"Peak Assignment": {
"accuracy": 15.79
},
"Basic Property Prediction": {
"accuracy": 29.41
}
}
},
"Semantic": {
"accuracy": 11.42,
"subcategories": {
"Molecular Structure Elucidation": {
"accuracy": 7.5
},
"Fusing Spectroscopic Modalities": {
"accuracy": 5.13
},
"Multimodal Molecular Reasoning": {
"accuracy": 21.62
}
}
},
"Generation": {
"accuracy": 0,
"subcategories": {
"Forward Problems": {
"accuracy": 0
},
"Inverse Problems": {
"accuracy": 0
},
"De Novo Generation": {
"accuracy": 0
}
}
},
"overall_accuracy": 14.84
},
"model_info": {
"homepage": "https://llama.meta.com/",
"paper": "https://arxiv.org/abs/2407.21783",
"code": "https://github.com/meta-llama/llama3",
"description": "Llama 3.2 11B with vision capabilities"
}
}
]
}