Upload README.md
Browse files
README.md
CHANGED
|
@@ -84,6 +84,17 @@ We evaluate Katanemo Arch-Function series on the [Berkeley Function-Calling Lead
|
|
| 84 |
<td>63.41%</td>
|
| 85 |
<td>82.93%</td>
|
| 86 |
</tr>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 87 |
<tr style="text-align: center; vertical-align: middle;">
|
| 88 |
<td>6</td>
|
| 89 |
<td>o1-preview-2024-09-12 (Prompt)</td>
|
|
@@ -95,17 +106,6 @@ We evaluate Katanemo Arch-Function series on the [Berkeley Function-Calling Lead
|
|
| 95 |
<td>73.17%</td>
|
| 96 |
<td>74.60%</td>
|
| 97 |
</tr>
|
| 98 |
-
<tr style="text-align: center; vertical-align: middle; font-weight: bold;">
|
| 99 |
-
<td> </td>
|
| 100 |
-
<td>Arch-Function-7B</td>
|
| 101 |
-
<td>58.44%</td>
|
| 102 |
-
<td>85.58%</td>
|
| 103 |
-
<td>88.14%</td>
|
| 104 |
-
<td>69.08%</td>
|
| 105 |
-
<td>20.50%</td>
|
| 106 |
-
<td>92.68%</td>
|
| 107 |
-
<td>74.05%</td>
|
| 108 |
-
</tr>
|
| 109 |
<tr style="text-align: center; vertical-align: middle; ">
|
| 110 |
<td>9</td>
|
| 111 |
<td>Gemini-1.5-Flash-002 (Prompt)</td>
|
|
@@ -117,6 +117,17 @@ We evaluate Katanemo Arch-Function series on the [Berkeley Function-Calling Lead
|
|
| 117 |
<td>85.37%</td>
|
| 118 |
<td>78.54%</td>
|
| 119 |
</tr>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 120 |
<tr style="text-align: center; vertical-align: middle; ">
|
| 121 |
<td>12</td>
|
| 122 |
<td>Claude-3.5-Sonnet-20240620 (FC)</td>
|
|
@@ -139,30 +150,17 @@ We evaluate Katanemo Arch-Function series on the [Berkeley Function-Calling Lead
|
|
| 139 |
<td>75.61%</td>
|
| 140 |
<td>49.44%</td>
|
| 141 |
</tr>
|
| 142 |
-
<tr style="text-align: center; vertical-align: middle; font-weight: bold;">
|
| 143 |
-
<td> </td>
|
| 144 |
-
<td>Arch-Function-3B</td>
|
| 145 |
-
<td>56.57%</td>
|
| 146 |
-
<td>83.62%</td>
|
| 147 |
-
<td>85.36%</td>
|
| 148 |
-
<td>66.90%</td>
|
| 149 |
-
<td>19.50%</td>
|
| 150 |
-
<td>97.56%</td>
|
| 151 |
-
<td>70.99%</td>
|
| 152 |
-
</tr>
|
| 153 |
-
</tr>
|
| 154 |
<tr style="text-align: center; vertical-align: middle; font-weight: bold;">
|
| 155 |
<td> </td>
|
| 156 |
<td>Arch-Function-1.5B</td>
|
| 157 |
-
<td>
|
| 158 |
-
<td>
|
| 159 |
-
<td>
|
| 160 |
-
<td>
|
| 161 |
-
<td>
|
| 162 |
-
<td>
|
| 163 |
-
<td>
|
| 164 |
</tr>
|
| 165 |
-
|
| 166 |
<tr style="text-align: center; vertical-align: middle; ">
|
| 167 |
<td>21</td>
|
| 168 |
<td>Llama-3.1-70B-Instruct (Prompt)</td>
|
|
|
|
| 84 |
<td>63.41%</td>
|
| 85 |
<td>82.93%</td>
|
| 86 |
</tr>
|
| 87 |
+
<tr style="text-align: center; vertical-align: middle; font-weight: bold;">
|
| 88 |
+
<td> </td>
|
| 89 |
+
<td>Arch-Function-7B</td>
|
| 90 |
+
<td>59.62%</td>
|
| 91 |
+
<td>86.83%</td>
|
| 92 |
+
<td>88.07%</td>
|
| 93 |
+
<td>71.57%</td>
|
| 94 |
+
<td>21.00%</td>
|
| 95 |
+
<td>95.12%</td>
|
| 96 |
+
<td>73.63%</td>
|
| 97 |
+
</tr>
|
| 98 |
<tr style="text-align: center; vertical-align: middle;">
|
| 99 |
<td>6</td>
|
| 100 |
<td>o1-preview-2024-09-12 (Prompt)</td>
|
|
|
|
| 106 |
<td>73.17%</td>
|
| 107 |
<td>74.60%</td>
|
| 108 |
</tr>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 109 |
<tr style="text-align: center; vertical-align: middle; ">
|
| 110 |
<td>9</td>
|
| 111 |
<td>Gemini-1.5-Flash-002 (Prompt)</td>
|
|
|
|
| 117 |
<td>85.37%</td>
|
| 118 |
<td>78.54%</td>
|
| 119 |
</tr>
|
| 120 |
+
<tr style="text-align: center; vertical-align: middle; font-weight: bold;">
|
| 121 |
+
<td> </td>
|
| 122 |
+
<td>Arch-Function-3B</td>
|
| 123 |
+
<td>57.69%</td>
|
| 124 |
+
<td>85.19%</td>
|
| 125 |
+
<td>86.18%</td>
|
| 126 |
+
<td>71.21%</td>
|
| 127 |
+
<td>17.50%</td>
|
| 128 |
+
<td>90.24%</td>
|
| 129 |
+
<td>72.88%</td>
|
| 130 |
+
</tr>
|
| 131 |
<tr style="text-align: center; vertical-align: middle; ">
|
| 132 |
<td>12</td>
|
| 133 |
<td>Claude-3.5-Sonnet-20240620 (FC)</td>
|
|
|
|
| 150 |
<td>75.61%</td>
|
| 151 |
<td>49.44%</td>
|
| 152 |
</tr>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 153 |
<tr style="text-align: center; vertical-align: middle; font-weight: bold;">
|
| 154 |
<td> </td>
|
| 155 |
<td>Arch-Function-1.5B</td>
|
| 156 |
+
<td>56.20%</td>
|
| 157 |
+
<td>84.40%</td>
|
| 158 |
+
<td>83.96%</td>
|
| 159 |
+
<td>69.36%</td>
|
| 160 |
+
<td>15.88%</td>
|
| 161 |
+
<td>87.80%</td>
|
| 162 |
+
<td>74.39%</td>
|
| 163 |
</tr>
|
|
|
|
| 164 |
<tr style="text-align: center; vertical-align: middle; ">
|
| 165 |
<td>21</td>
|
| 166 |
<td>Llama-3.1-70B-Instruct (Prompt)</td>
|