Initial commit

.gitignore

@@ -0,0 +1,2 @@
+.DS_store
+.idea

README.md

@@ -0,0 +1,6 @@
+# MathVista
+
+This website is adapted from [Nerfies website](https://nerfies.github.io).
+
+# Website License
+<a rel="license" href="http://creativecommons.org/licenses/by-sa/4.0/"><img alt="Creative Commons License" style="border-width:0" src="https://i.creativecommons.org/l/by-sa/4.0/88x31.png" /></a><br />This work is licensed under a <a rel="license" href="http://creativecommons.org/licenses/by-sa/4.0/">Creative Commons Attribution-ShareAlike 4.0 International License</a>.

data/results/Claude 3 Haiku/meta.json

@@ -0,0 +1,6 @@
+{
+    "Method": "LMM 🖼️",
+    "Source": "https://www-cdn.anthropic.com/de8ba9b01c9ab7cbabf5c33b80b7bbc618857627/Model_Card_Claude_3.pdf",
+    "Date": "2024-03-04",
+    "Comment": ""
+}

data/results/Claude 3 Haiku/scores_claude3_haiku_testmini.json

@@ -0,0 +1,45 @@
+{
+  "average": {
+    "accuracy": "46.4"
+  },
+  "task": {
+    "figure question answering": {
+      "accuracy": "-"
+    },
+    "geometry problem solving": {
+      "accuracy": "-"
+    },
+    "math word problem": {
+      "accuracy": "-"
+    },
+    "textbook question answering": {
+      "accuracy": "-"
+    },
+    "visual question answering": {
+      "accuracy": "-"
+    }
+  },
+  "skills": {
+    "algebraic reasoning": {
+      "accuracy": "-"
+    },
+    "arithmetic reasoning": {
+      "accuracy": "-"
+    },
+    "geometry reasoning": {
+      "accuracy": "-"
+    },
+    "logical reasoning": {
+      "accuracy": "-"
+    },
+    "numeric commonsense": {
+      "accuracy": "-"
+    },
+    "scientific reasoning": {
+      "accuracy": "-"
+    },
+    "statistical reasoning": {
+      "accuracy": "-"
+    }
+  }
+}

data/results/Claude 3 Opus/meta.json

@@ -0,0 +1,6 @@
+{
+    "Method": "LMM 🖼️",
+    "Source": "https://www-cdn.anthropic.com/de8ba9b01c9ab7cbabf5c33b80b7bbc618857627/Model_Card_Claude_3.pdf",
+    "Date": "2024-03-04",
+    "Comment": ""
+}

data/results/Claude 3 Opus/scores_claude3_opus_testmini.json

@@ -0,0 +1,45 @@
+{
+  "average": {
+    "accuracy": "50.5"
+  },
+  "task": {
+    "figure question answering": {
+      "accuracy": "-"
+    },
+    "geometry problem solving": {
+      "accuracy": "-"
+    },
+    "math word problem": {
+      "accuracy": "-"
+    },
+    "textbook question answering": {
+      "accuracy": "-"
+    },
+    "visual question answering": {
+      "accuracy": "-"
+    }
+  },
+  "skills": {
+    "algebraic reasoning": {
+      "accuracy": "-"
+    },
+    "arithmetic reasoning": {
+      "accuracy": "-"
+    },
+    "geometry reasoning": {
+      "accuracy": "-"
+    },
+    "logical reasoning": {
+      "accuracy": "-"
+    },
+    "numeric commonsense": {
+      "accuracy": "-"
+    },
+    "scientific reasoning": {
+      "accuracy": "-"
+    },
+    "statistical reasoning": {
+      "accuracy": "-"
+    }
+  }
+}

data/results/Claude 3 Sonnet/meta.json

@@ -0,0 +1,6 @@
+{
+    "Method": "LMM 🖼️",
+    "Source": "https://www-cdn.anthropic.com/de8ba9b01c9ab7cbabf5c33b80b7bbc618857627/Model_Card_Claude_3.pdf",
+    "Date": "2024-03-04",
+    "Comment": ""
+}

data/results/Claude 3 Sonnet/scores_claude3_sonnet_testmini.json

@@ -0,0 +1,45 @@
+{
+  "average": {
+    "accuracy": "47.9"
+  },
+  "task": {
+    "figure question answering": {
+      "accuracy": "-"
+    },
+    "geometry problem solving": {
+      "accuracy": "-"
+    },
+    "math word problem": {
+      "accuracy": "-"
+    },
+    "textbook question answering": {
+      "accuracy": "-"
+    },
+    "visual question answering": {
+      "accuracy": "-"
+    }
+  },
+  "skills": {
+    "algebraic reasoning": {
+      "accuracy": "-"
+    },
+    "arithmetic reasoning": {
+      "accuracy": "-"
+    },
+    "geometry reasoning": {
+      "accuracy": "-"
+    },
+    "logical reasoning": {
+      "accuracy": "-"
+    },
+    "numeric commonsense": {
+      "accuracy": "-"
+    },
+    "scientific reasoning": {
+      "accuracy": "-"
+    },
+    "statistical reasoning": {
+      "accuracy": "-"
+    }
+  }
+}

data/results/Claude 3.5 Sonnet/meta.json

@@ -0,0 +1,6 @@
+{
+    "Method": "LMM 🖼️",
+    "Source": "https://www.anthropic.com/news/claude-3-5-sonnet",
+    "Date": "2024-06-20",
+    "Comment": ""
+}

data/results/Claude 3.5 Sonnet/scores_claude3.5_sonnet_testmini.json

@@ -0,0 +1,45 @@
+{
+  "average": {
+    "accuracy": "67.7"
+  },
+  "task": {
+    "figure question answering": {
+      "accuracy": "-"
+    },
+    "geometry problem solving": {
+      "accuracy": "-"
+    },
+    "math word problem": {
+      "accuracy": "-"
+    },
+    "textbook question answering": {
+      "accuracy": "-"
+    },
+    "visual question answering": {
+      "accuracy": "-"
+    }
+  },
+  "skills": {
+    "algebraic reasoning": {
+      "accuracy": "-"
+    },
+    "arithmetic reasoning": {
+      "accuracy": "-"
+    },
+    "geometry reasoning": {
+      "accuracy": "-"
+    },
+    "logical reasoning": {
+      "accuracy": "-"
+    },
+    "numeric commonsense": {
+      "accuracy": "-"
+    },
+    "scientific reasoning": {
+      "accuracy": "-"
+    },
+    "statistical reasoning": {
+      "accuracy": "-"
+    }
+  }
+}

data/results/CoT ChatGPT (Caption+OCR)/meta.json

@@ -0,0 +1,6 @@
+{
+    "Method": "Tool 🛠️",
+    "Source": "https://arxiv.org/abs/2310.02255",
+    "Date": "2023-10-03",
+    "Comment": ""
+}