Align leaderboard with SpectrumWorld paper Table 3

leaderboard_v_1.0.json

@@ -1,8 +1,251 @@
 {
     "leaderboard_info": {
-        "total_models": 18
+        "total_models": 23
     },
     "models": [
+        {
+            "name": "Gemini-2.5-pro",
+            "submission_time": "2025-08-01T17:09:29.900000Z",
+            "results": {
+                "Signal": {
+                    "accuracy": 72.36,
+                    "subcategories": {
+                        "Spectrum Type Classification": {
+                            "accuracy": 96.36
+                        },
+                        "Spectrum Quality Assessment": {
+                            "accuracy": 35.0
+                        },
+                        "Basic Feature Extraction": {
+                            "accuracy": 90.2
+                        },
+                        "Impurity Peak Detection": {
+                            "accuracy": 67.86
+                        }
+                    }
+                },
+                "Perception": {
+                    "accuracy": 76.72,
+                    "subcategories": {
+                        "Functional Group Recognition": {
+                            "accuracy": 75.56
+                        },
+                        "Elemental Compositional Prediction": {
+                            "accuracy": 86.11
+                        },
+                        "Peak Assignment": {
+                            "accuracy": 65.79
+                        },
+                        "Basic Property Prediction": {
+                            "accuracy": 79.41
+                        }
+                    }
+                },
+                "Semantic": {
+                    "accuracy": 83.56,
+                    "subcategories": {
+                        "Molecular Structure Elucidation": {
+                            "accuracy": 68.75
+                        },
+                        "Fusing Spectroscopic Modalities": {
+                            "accuracy": 84.62
+                        },
+                        "Multimodal Molecular Reasoning": {
+                            "accuracy": 97.3
+                        }
+                    }
+                },
+                "Generation": {
+                    "accuracy": 34.12,
+                    "subcategories": {
+                        "Forward Problems": {
+                            "accuracy": 50.0
+                        },
+                        "Inverse Problems": {
+                            "accuracy": 5.0
+                        },
+                        "De Novo Generation": {
+                            "accuracy": 47.37
+                        }
+                    }
+                },
+                "overall_accuracy": 67.81
+            },
+            "name_link": "https://deepmind.google/models/gemini/pro/",
+            "submitter": "Google DeepMind",
+            "submitter_link": "https://deepmind.google/",
+            "model_type": "proprietary",
+            "model_size": "Unknown",
+            "is_multimodal": true,
+            "model_info": {
+                "homepage": "https://deepmind.google/models/gemini/pro/",
+                "paper": "",
+                "code": "",
+                "description": "Gemini 2.5 Pro multimodal model reported in SpectrumWorld Table 3."
+            }
+        },
+        {
+            "name": "InternVL3.5-241B",
+            "submission_time": "2025-08-01T17:09:29.900000Z",
+            "results": {
+                "Signal": {
+                    "accuracy": 78.64,
+                    "subcategories": {
+                        "Spectrum Type Classification": {
+                            "accuracy": 98.18
+                        },
+                        "Spectrum Quality Assessment": {
+                            "accuracy": 33.33
+                        },
+                        "Basic Feature Extraction": {
+                            "accuracy": 90.2
+                        },
+                        "Impurity Peak Detection": {
+                            "accuracy": 92.86
+                        }
+                    }
+                },
+                "Perception": {
+                    "accuracy": 75.2,
+                    "subcategories": {
+                        "Functional Group Recognition": {
+                            "accuracy": 66.67
+                        },
+                        "Elemental Compositional Prediction": {
+                            "accuracy": 77.78
+                        },
+                        "Peak Assignment": {
+                            "accuracy": 71.05
+                        },
+                        "Basic Property Prediction": {
+                            "accuracy": 85.29
+                        }
+                    }
+                },
+                "Semantic": {
+                    "accuracy": 82.6,
+                    "subcategories": {
+                        "Molecular Structure Elucidation": {
+                            "accuracy": 86.25
+                        },
+                        "Fusing Spectroscopic Modalities": {
+                            "accuracy": 61.54
+                        },
+                        "Multimodal Molecular Reasoning": {
+                            "accuracy": 100.0
+                        }
+                    }
+                },
+                "Generation": {
+                    "accuracy": 17.95,
+                    "subcategories": {
+                        "Forward Problems": {
+                            "accuracy": 33.33
+                        },
+                        "Inverse Problems": {
+                            "accuracy": 10.0
+                        },
+                        "De Novo Generation": {
+                            "accuracy": 10.53
+                        }
+                    }
+                },
+                "overall_accuracy": 65.5
+            },
+            "name_link": "https://internvl.github.io/",
+            "submitter": "InternVL Team",
+            "submitter_link": "https://internvl.github.io/",
+            "model_type": "open_source",
+            "model_size": "241B",
+            "is_multimodal": true,
+            "model_info": {
+                "homepage": "https://internvl.github.io/",
+                "paper": "",
+                "code": "https://github.com/OpenGVLab/InternVL",
+                "description": "InternVL3.5 241B model reported in SpectrumWorld Table 3."
+            }
+        },
+        {
+            "name": "InternS1-think",
+            "submission_time": "2025-08-01T17:09:29.900000Z",
+            "results": {
+                "Signal": {
+                    "accuracy": 73.22,
+                    "subcategories": {
+                        "Spectrum Type Classification": {
+                            "accuracy": 98.18
+                        },
+                        "Spectrum Quality Assessment": {
+                            "accuracy": 25.0
+                        },
+                        "Basic Feature Extraction": {
+                            "accuracy": 80.39
+                        },
+                        "Impurity Peak Detection": {
+                            "accuracy": 89.29
+                        }
+                    }
+                },
+                "Perception": {
+                    "accuracy": 79.55,
+                    "subcategories": {
+                        "Functional Group Recognition": {
+                            "accuracy": 64.44
+                        },
+                        "Elemental Compositional Prediction": {
+                            "accuracy": 88.89
+                        },
+                        "Peak Assignment": {
+                            "accuracy": 73.68
+                        },
+                        "Basic Property Prediction": {
+                            "accuracy": 91.18
+                        }
+                    }
+                },
+                "Semantic": {
+                    "accuracy": 79.43,
+                    "subcategories": {
+                        "Molecular Structure Elucidation": {
+                            "accuracy": 90.0
+                        },
+                        "Fusing Spectroscopic Modalities": {
+                            "accuracy": 56.41
+                        },
+                        "Multimodal Molecular Reasoning": {
+                            "accuracy": 91.89
+                        }
+                    }
+                },
+                "Generation": {
+                    "accuracy": 21.93,
+                    "subcategories": {
+                        "Forward Problems": {
+                            "accuracy": 10.0
+                        },
+                        "Inverse Problems": {
+                            "accuracy": 40.0
+                        },
+                        "De Novo Generation": {
+                            "accuracy": 15.79
+                        }
+                    }
+                },
+                "overall_accuracy": 65.37
+            },
+            "name_link": "https://internvl.github.io/",
+            "submitter": "InternVL Team",
+            "submitter_link": "https://internvl.github.io/",
+            "model_type": "open_source",
+            "model_size": "Unknown",
+            "is_multimodal": true,
+            "model_info": {
+                "homepage": "https://internvl.github.io/",
+                "paper": "",
+                "code": "https://github.com/OpenGVLab/InternVL",
+                "description": "InternS1 thinking setting reported in SpectrumWorld Table 3."
+            }
+        },
         {
             "name": "Claude-3.7-Sonnet",
             "name_link": "https://www.anthropic.com/claude",
@@ -75,7 +318,7 @@
                         }
                     }
                 },
-                "overall_accuracy": 61.51
+                "overall_accuracy": 63.84
             },
             "model_info": {
                 "homepage": "https://www.anthropic.com/claude",
@@ -156,7 +399,7 @@
                         }
                     }
                 },
-                "overall_accuracy": 61.38
+                "overall_accuracy": 62.9
             },
             "model_info": {
                 "homepage": "https://www.volcengine.com/product/doubao",
@@ -166,7 +409,7 @@
             }
         },
         {
-            "name": "Qwen2.5-VL-72B-Instruct",
+            "name": "Qwen2.5-VL-72B",
             "name_link": "https://qwenlm.github.io/",
             "submitter": "Alibaba DAMO Academy",
             "submitter_link": "https://damo.alibaba.com/",
@@ -237,7 +480,7 @@
                         }
                     }
                 },
-                "overall_accuracy": 60.59
+                "overall_accuracy": 62.68
             },
             "model_info": {
                 "homepage": "https://qwenlm.github.io/",
@@ -246,6 +489,87 @@
                 "description": "Qwen2.5-VL-72B large-scale open-source vision-language model"
             }
         },
+        {
+            "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": 61.91
+            },
+            "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-4.1",
             "name_link": "https://openai.com/gpt-4",
@@ -318,7 +642,7 @@
                         }
                     }
                 },
-                "overall_accuracy": 59.28
+                "overall_accuracy": 60.96
             },
             "model_info": {
                 "homepage": "https://openai.com/gpt-4",
@@ -328,26 +652,26 @@
             }
         },
         {
-            "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",
+            "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": 78.57,
+                    "accuracy": 73.32,
                     "subcategories": {
                         "Spectrum Type Classification": {
                             "accuracy": 94.55
                         },
                         "Spectrum Quality Assessment": {
-                            "accuracy": 36.67
+                            "accuracy": 33.33
                         },
                         "Basic Feature Extraction": {
-                            "accuracy": 90.2
+                            "accuracy": 72.55
                         },
                         "Impurity Peak Detection": {
                             "accuracy": 92.86
@@ -355,80 +679,80 @@
                     }
                 },
                 "Perception": {
-                    "accuracy": 76.94,
+                    "accuracy": 74.74,
                     "subcategories": {
                         "Functional Group Recognition": {
-                            "accuracy": 60.0
+                            "accuracy": 73.33
                         },
                         "Elemental Compositional Prediction": {
-                            "accuracy": 80.56
+                            "accuracy": 72.22
                         },
                         "Peak Assignment": {
-                            "accuracy": 78.95
+                            "accuracy": 71.05
                         },
                         "Basic Property Prediction": {
-                            "accuracy": 88.24
+                            "accuracy": 82.35
                         }
                     }
                 },
                 "Semantic": {
-                    "accuracy": 65.39,
+                    "accuracy": 74.97,
                     "subcategories": {
                         "Molecular Structure Elucidation": {
-                            "accuracy": 32.5
+                            "accuracy": 73.75
                         },
                         "Fusing Spectroscopic Modalities": {
-                            "accuracy": 71.79
+                            "accuracy": 53.85
                         },
                         "Multimodal Molecular Reasoning": {
-                            "accuracy": 91.89
+                            "accuracy": 97.3
                         }
                     }
                 },
                 "Generation": {
-                    "accuracy": 16.2,
+                    "accuracy": 9.44,
                     "subcategories": {
                         "Forward Problems": {
-                            "accuracy": 43.33
+                            "accuracy": 23.33
                         },
                         "Inverse Problems": {
-                            "accuracy": 0
+                            "accuracy": 5.0
                         },
                         "De Novo Generation": {
-                            "accuracy": 5.26
+                            "accuracy": 0
                         }
                     }
                 },
-                "overall_accuracy": 59.27
+                "overall_accuracy": 60.39
             },
             "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"
+                "homepage": "https://openai.com/gpt-4",
+                "paper": "https://arxiv.org/abs/2303.08774",
+                "code": "",
+                "description": "GPT-4 with vision capabilities for multimodal 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",
+            "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": 73.32,
+                    "accuracy": 77.2,
                     "subcategories": {
                         "Spectrum Type Classification": {
-                            "accuracy": 94.55
+                            "accuracy": 96.36
                         },
                         "Spectrum Quality Assessment": {
                             "accuracy": 33.33
                         },
                         "Basic Feature Extraction": {
-                            "accuracy": 72.55
+                            "accuracy": 86.27
                         },
                         "Impurity Peak Detection": {
                             "accuracy": 92.86
@@ -436,57 +760,57 @@
                     }
                 },
                 "Perception": {
-                    "accuracy": 74.74,
+                    "accuracy": 78.25,
                     "subcategories": {
                         "Functional Group Recognition": {
                             "accuracy": 73.33
                         },
                         "Elemental Compositional Prediction": {
-                            "accuracy": 72.22
+                            "accuracy": 83.33
                         },
                         "Peak Assignment": {
                             "accuracy": 71.05
                         },
                         "Basic Property Prediction": {
-                            "accuracy": 82.35
+                            "accuracy": 85.29
                         }
                     }
                 },
                 "Semantic": {
-                    "accuracy": 74.97,
+                    "accuracy": 65.3,
                     "subcategories": {
                         "Molecular Structure Elucidation": {
-                            "accuracy": 73.75
+                            "accuracy": 32.5
                         },
                         "Fusing Spectroscopic Modalities": {
-                            "accuracy": 53.85
+                            "accuracy": 76.92
                         },
                         "Multimodal Molecular Reasoning": {
-                            "accuracy": 97.3
+                            "accuracy": 86.49
                         }
                     }
                 },
                 "Generation": {
-                    "accuracy": 9.44,
+                    "accuracy": 7.31,
                     "subcategories": {
                         "Forward Problems": {
-                            "accuracy": 23.33
+                            "accuracy": 16.67
                         },
                         "Inverse Problems": {
-                            "accuracy": 5.0
+                            "accuracy": 0
                         },
                         "De Novo Generation": {
-                            "accuracy": 0
+                            "accuracy": 5.26
                         }
                     }
                 },
-                "overall_accuracy": 58.12
+                "overall_accuracy": 59.98
             },
             "model_info": {
-                "homepage": "https://openai.com/gpt-4",
-                "paper": "https://arxiv.org/abs/2303.08774",
+                "homepage": "https://www.anthropic.com/claude",
+                "paper": "",
                 "code": "",
-                "description": "GPT-4 with vision capabilities for multimodal understanding"
+                "description": "Claude 4 Opus - most capable model in the Claude family"
             }
         },
         {
@@ -561,7 +885,7 @@
                         }
                     }
                 },
-                "overall_accuracy": 57.95
+                "overall_accuracy": 59.88
             },
             "model_info": {
                 "homepage": "https://www.anthropic.com/claude",
@@ -571,26 +895,20 @@
             }
         },
         {
-            "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,
+            "name": "GLM-4.5V",
+            "submission_time": "2025-08-01T17:09:29.900000Z",
             "results": {
                 "Signal": {
-                    "accuracy": 77.2,
+                    "accuracy": 72.94,
                     "subcategories": {
                         "Spectrum Type Classification": {
-                            "accuracy": 96.36
+                            "accuracy": 100.0
                         },
                         "Spectrum Quality Assessment": {
-                            "accuracy": 33.33
+                            "accuracy": 28.33
                         },
                         "Basic Feature Extraction": {
-                            "accuracy": 86.27
+                            "accuracy": 70.59
                         },
                         "Impurity Peak Detection": {
                             "accuracy": 92.86
@@ -598,7 +916,7 @@
                     }
                 },
                 "Perception": {
-                    "accuracy": 78.25,
+                    "accuracy": 79.72,
                     "subcategories": {
                         "Functional Group Recognition": {
                             "accuracy": 73.33
@@ -610,45 +928,132 @@
                             "accuracy": 71.05
                         },
                         "Basic Property Prediction": {
-                            "accuracy": 85.29
+                            "accuracy": 91.18
                         }
                     }
                 },
                 "Semantic": {
-                    "accuracy": 65.3,
+                    "accuracy": 72.25,
                     "subcategories": {
                         "Molecular Structure Elucidation": {
-                            "accuracy": 32.5
+                            "accuracy": 63.75
                         },
                         "Fusing Spectroscopic Modalities": {
-                            "accuracy": 76.92
+                            "accuracy": 69.23
                         },
                         "Multimodal Molecular Reasoning": {
-                            "accuracy": 86.49
+                            "accuracy": 83.78
                         }
                     }
                 },
                 "Generation": {
-                    "accuracy": 7.31,
+                    "accuracy": 3.51,
                     "subcategories": {
                         "Forward Problems": {
-                            "accuracy": 16.67
+                            "accuracy": 0.0
                         },
                         "Inverse Problems": {
-                            "accuracy": 0
+                            "accuracy": 0.0
                         },
                         "De Novo Generation": {
-                            "accuracy": 5.26
+                            "accuracy": 10.53
                         }
                     }
                 },
-                "overall_accuracy": 57.02
+                "overall_accuracy": 59.85
             },
+            "name_link": "https://github.com/zai-org/GLM-V",
+            "submitter": "Zhipu AI",
+            "submitter_link": "https://www.zhipuai.cn/",
+            "model_type": "open_source",
+            "model_size": "Unknown",
+            "is_multimodal": true,
             "model_info": {
-                "homepage": "https://www.anthropic.com/claude",
+                "homepage": "https://github.com/zai-org/GLM-V",
                 "paper": "",
-                "code": "",
-                "description": "Claude 4 Opus - most capable model in the Claude family"
+                "code": "https://github.com/zai-org/GLM-V",
+                "description": "GLM-4.5V model reported in SpectrumWorld Table 3."
+            }
+        },
+        {
+            "name": "InternS1-nothink",
+            "submission_time": "2025-08-01T17:09:29.900000Z",
+            "results": {
+                "Signal": {
+                    "accuracy": 74.17,
+                    "subcategories": {
+                        "Spectrum Type Classification": {
+                            "accuracy": 98.18
+                        },
+                        "Spectrum Quality Assessment": {
+                            "accuracy": 36.67
+                        },
+                        "Basic Feature Extraction": {
+                            "accuracy": 72.55
+                        },
+                        "Impurity Peak Detection": {
+                            "accuracy": 89.29
+                        }
+                    }
+                },
+                "Perception": {
+                    "accuracy": 69.11,
+                    "subcategories": {
+                        "Functional Group Recognition": {
+                            "accuracy": 51.11
+                        },
+                        "Elemental Compositional Prediction": {
+                            "accuracy": 72.22
+                        },
+                        "Peak Assignment": {
+                            "accuracy": 73.68
+                        },
+                        "Basic Property Prediction": {
+                            "accuracy": 79.41
+                        }
+                    }
+                },
+                "Semantic": {
+                    "accuracy": 82.5,
+                    "subcategories": {
+                        "Molecular Structure Elucidation": {
+                            "accuracy": 86.25
+                        },
+                        "Fusing Spectroscopic Modalities": {
+                            "accuracy": 66.67
+                        },
+                        "Multimodal Molecular Reasoning": {
+                            "accuracy": 94.59
+                        }
+                    }
+                },
+                "Generation": {
+                    "accuracy": 4.44,
+                    "subcategories": {
+                        "Forward Problems": {
+                            "accuracy": 13.33
+                        },
+                        "Inverse Problems": {
+                            "accuracy": 0.0
+                        },
+                        "De Novo Generation": {
+                            "accuracy": 0.0
+                        }
+                    }
+                },
+                "overall_accuracy": 59.57
+            },
+            "name_link": "https://internvl.github.io/",
+            "submitter": "InternVL Team",
+            "submitter_link": "https://internvl.github.io/",
+            "model_type": "open_source",
+            "model_size": "Unknown",
+            "is_multimodal": true,
+            "model_info": {
+                "homepage": "https://internvl.github.io/",
+                "paper": "",
+                "code": "https://github.com/OpenGVLab/InternVL",
+                "description": "InternS1 no-thinking setting reported in SpectrumWorld Table 3."
             }
         },
         {
@@ -723,7 +1128,7 @@
                         }
                     }
                 },
-                "overall_accuracy": 56.4
+                "overall_accuracy": 59.23
             },
             "model_info": {
                 "homepage": "https://www.volcengine.com/product/doubao",
@@ -804,7 +1209,7 @@
                         }
                     }
                 },
-                "overall_accuracy": 55.97
+                "overall_accuracy": 58.15
             },
             "model_info": {
                 "homepage": "https://internvl.github.io/",
@@ -841,10 +1246,10 @@
                     }
                 },
                 "Perception": {
-                    "accuracy": 69.53,
+                    "accuracy": 70.06,
                     "subcategories": {
                         "Functional Group Recognition": {
-                            "accuracy": 57.78
+                            "accuracy": 59.88
                         },
                         "Elemental Compositional Prediction": {
                             "accuracy": 77.78
@@ -858,7 +1263,7 @@
                     }
                 },
                 "Semantic": {
-                    "accuracy": 77.44,
+                    "accuracy": 75.64,
                     "subcategories": {
                         "Molecular Structure Elucidation": {
                             "accuracy": 78.75
@@ -867,7 +1272,7 @@
                             "accuracy": 58.97
                         },
                         "Multimodal Molecular Reasoning": {
-                            "accuracy": 94.59
+                            "accuracy": 89.19
                         }
                     }
                 },
@@ -885,7 +1290,7 @@
                         }
                     }
                 },
-                "overall_accuracy": 55.77
+                "overall_accuracy": 57.74
             },
             "model_info": {
                 "homepage": "https://openai.com/gpt-4",
@@ -966,7 +1371,7 @@
                         }
                     }
                 },
-                "overall_accuracy": 54.32
+                "overall_accuracy": 57.12
             },
             "model_info": {
                 "homepage": "https://grok.x.ai/",
@@ -1047,7 +1452,7 @@
                         }
                     }
                 },
-                "overall_accuracy": 53.84
+                "overall_accuracy": 56.23
             },
             "model_info": {
                 "homepage": "https://www.anthropic.com/claude",
@@ -1128,7 +1533,7 @@
                         }
                     }
                 },
-                "overall_accuracy": 48.4
+                "overall_accuracy": 51.76
             },
             "model_info": {
                 "homepage": "https://www.anthropic.com/claude",
@@ -1138,7 +1543,7 @@
             }
         },
         {
-            "name": "Qwen2.5-VL-32B-Instruct",
+            "name": "Qwen2.5-VL-32B",
             "name_link": "https://qwenlm.github.io/",
             "submitter": "Alibaba DAMO Academy",
             "submitter_link": "https://damo.alibaba.com/",
@@ -1209,7 +1614,7 @@
                         }
                     }
                 },
-                "overall_accuracy": 32.4
+                "overall_accuracy": 35.34
             },
             "model_info": {
                 "homepage": "https://qwenlm.github.io/",
@@ -1290,7 +1695,7 @@
                         }
                     }
                 },
-                "overall_accuracy": 22.53
+                "overall_accuracy": 23.77
             },
             "model_info": {
                 "homepage": "https://www.deepseek.com/",
@@ -1358,7 +1763,7 @@
                     }
                 },
                 "Generation": {
-                    "accuracy": 0,
+                    "accuracy": 0.0,
                     "subcategories": {
                         "Forward Problems": {
                             "accuracy": 0
@@ -1371,7 +1776,7 @@
                         }
                     }
                 },
-                "overall_accuracy": 18.52
+                "overall_accuracy": 19.51
             },
             "model_info": {
                 "homepage": "https://llama.meta.com/",
@@ -1439,7 +1844,7 @@
                     }
                 },
                 "Generation": {
-                    "accuracy": 0,
+                    "accuracy": 0.0,
                     "subcategories": {
                         "Forward Problems": {
                             "accuracy": 0
@@ -1452,7 +1857,7 @@
                         }
                     }
                 },
-                "overall_accuracy": 14.84
+                "overall_accuracy": 16.15
             },
             "model_info": {
                 "homepage": "https://llama.meta.com/",
@@ -1462,4 +1867,4 @@
             }
         }
     ]
-}
+}