Skip to content

Commit 1fef52f

Browse files
committed
add sample mistral results/renders
1 parent 59fd500 commit 1fef52f

File tree

122 files changed

+1330
-3
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

122 files changed

+1330
-3
lines changed

docs/archive/overview.md

Lines changed: 8 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -43,6 +43,14 @@ This page provides an overview of all benchmark tests.Click on the test name to
4343

4444
</tr></thead>
4545
<tbody>
46+
<tr>
47+
<td>2025-04-02</td>
48+
<td></td>
49+
<td><a href='/archive/2025-04-02/T22'><span class='test-square' style='background-color: #2980b9;'>T22</span></a>&nbsp;</td>
50+
<td><a href='/archive/2025-04-02/T23'><span class='test-square' style='background-color: #ff0066;'>T23</span></a>&nbsp;</td>
51+
<td></td>
52+
<td></td>
53+
</tr>
4654
<tr>
4755
<td>2025-04-01</td>
4856
<td><a href='/archive/2025-04-01/T07'><span class='test-square' style='background-color: #ff99cc;'>T07</span></a>&nbsp;<a href='/archive/2025-04-01/T08'><span class='test-square' style='background-color: #ffcc33;'>T08</span></a>&nbsp;<a href='/archive/2025-04-01/T09'><span class='test-square' style='background-color: #ff0066;'>T09</span></a>&nbsp;</td>

docs/index.md

Lines changed: 5 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -56,7 +56,11 @@ results, and comparisons.
5656
</tr>
5757
<tr>
5858
<td>metadata_extraction</td>
59-
<td><a href='archive/2025-04-01/T10'><span class='test-square' style='background-color: #ff6600;'>T10</span></a>: 2025-04-01 <img src="https://img.shields.io/badge/f1_macro-0.52045159194282-brightgreen" alt="f1_macro"> <img src="https://img.shields.io/badge/f1_micro-0.5231788079470199-brightgreen" alt="f1_micro"><br><a href='archive/2025-04-01/T11'><span class='test-square' style='background-color: #ff6600;'>T11</span></a>: 2025-04-01 <img src="https://img.shields.io/badge/f1_macro-0.5502508051447442-brightgreen" alt="f1_macro"> <img src="https://img.shields.io/badge/f1_micro-0.5793103448275863-brightgreen" alt="f1_micro"><br><a href='archive/2025-04-01/T12'><span class='test-square' style='background-color: #6633ff;'>T12</span></a>: 2025-04-01 <img src="https://img.shields.io/badge/f1_macro-0.5085154955123995-brightgreen" alt="f1_macro"> <img src="https://img.shields.io/badge/f1_micro-0.511326860841424-brightgreen" alt="f1_micro"><br><a href='archive/2025-04-01/T13'><span class='test-square' style='background-color: #ff6600;'>T13</span></a>: 2025-04-01 <img src="https://img.shields.io/badge/f1_macro-0.46274808931963324-brightgreen" alt="f1_macro"> <img src="https://img.shields.io/badge/f1_micro-0.4585987261146497-brightgreen" alt="f1_micro"><br><a href='archive/2025-04-01/T14'><span class='test-square' style='background-color: #34495e;'>T14</span></a>: 2025-04-01 <img src="https://img.shields.io/badge/f1_macro-0.554063932353406-brightgreen" alt="f1_macro"> <img src="https://img.shields.io/badge/f1_micro-0.5704225352112676-brightgreen" alt="f1_micro"><br><a href='archive/2025-04-01/T15'><span class='test-square' style='background-color: #ff0099;'>T15</span></a>: 2025-04-01 <img src="https://img.shields.io/badge/f1_macro-0.3694170771756979-brightgreen" alt="f1_macro"> <img src="https://img.shields.io/badge/f1_micro-0.3701298701298701-brightgreen" alt="f1_micro"><br><a href='archive/2025-04-01/T16'><span class='test-square' style='background-color: #33ffcc;'>T16</span></a>: 2025-04-01 <img src="https://img.shields.io/badge/f1_macro-0.43630472577841-brightgreen" alt="f1_macro"> <img src="https://img.shields.io/badge/f1_micro-0.43278688524590164-brightgreen" alt="f1_micro"><br><a href='archive/2025-04-01/T17'><span class='test-square' style='background-color: #9b59b6;'>T17</span></a>: 2025-04-01 <img src="https://img.shields.io/badge/f1_macro-0.42966944328105855-brightgreen" alt="f1_macro"> <img src="https://img.shields.io/badge/f1_micro-0.43934426229508194-brightgreen" alt="f1_micro"><br><a href='archive/2025-04-01/T18'><span class='test-square' style='background-color: #99ff33;'>T18</span></a>: 2025-04-01 <img src="https://img.shields.io/badge/f1_macro-0.42007290954659376-brightgreen" alt="f1_macro"> <img src="https://img.shields.io/badge/f1_micro-0.42996742671009774-brightgreen" alt="f1_micro"><br><a href='archive/2025-04-01/T19'><span class='test-square' style='background-color: #0099ff;'>T19</span></a>: 2025-04-01 <img src="https://img.shields.io/badge/f1_macro-0.5612242959703547-brightgreen" alt="f1_macro"> <img src="https://img.shields.io/badge/f1_micro-0.5774647887323944-brightgreen" alt="f1_micro"><br><a href='archive/2025-04-01/T20'><span class='test-square' style='background-color: #ff5050;'>T20</span></a>: 2025-04-01 <img src="https://img.shields.io/badge/f1_macro-0.4940796180052578-brightgreen" alt="f1_macro"> <img src="https://img.shields.io/badge/f1_micro-0.49504950495049505-brightgreen" alt="f1_micro"><br><a href='archive/2025-04-01/T21'><span class='test-square' style='background-color: #9933ff;'>T21</span></a>: 2025-04-01 <img src="https://img.shields.io/badge/f1_macro-0.5516959064327486-brightgreen" alt="f1_macro"> <img src="https://img.shields.io/badge/f1_micro-0.5655172413793104-brightgreen" alt="f1_micro"><br></td>
59+
<td><a href='archive/2025-04-01/T10'><span class='test-square' style='background-color: #ff6600;'>T10</span></a>: 2025-04-01 <img src="https://img.shields.io/badge/f1_macro-0.52045159194282-brightgreen" alt="f1_macro"> <img src="https://img.shields.io/badge/f1_micro-0.5231788079470199-brightgreen" alt="f1_micro"><br><a href='archive/2025-04-01/T11'><span class='test-square' style='background-color: #ff6600;'>T11</span></a>: 2025-04-01 <img src="https://img.shields.io/badge/f1_macro-0.5502508051447442-brightgreen" alt="f1_macro"> <img src="https://img.shields.io/badge/f1_micro-0.5793103448275863-brightgreen" alt="f1_micro"><br><a href='archive/2025-04-01/T12'><span class='test-square' style='background-color: #6633ff;'>T12</span></a>: 2025-04-01 <img src="https://img.shields.io/badge/f1_macro-0.5085154955123995-brightgreen" alt="f1_macro"> <img src="https://img.shields.io/badge/f1_micro-0.511326860841424-brightgreen" alt="f1_micro"><br><a href='archive/2025-04-01/T13'><span class='test-square' style='background-color: #ff6600;'>T13</span></a>: 2025-04-01 <img src="https://img.shields.io/badge/f1_macro-0.46274808931963324-brightgreen" alt="f1_macro"> <img src="https://img.shields.io/badge/f1_micro-0.4585987261146497-brightgreen" alt="f1_micro"><br><a href='archive/2025-04-01/T14'><span class='test-square' style='background-color: #34495e;'>T14</span></a>: 2025-04-01 <img src="https://img.shields.io/badge/f1_macro-0.554063932353406-brightgreen" alt="f1_macro"> <img src="https://img.shields.io/badge/f1_micro-0.5704225352112676-brightgreen" alt="f1_micro"><br><a href='archive/2025-04-01/T15'><span class='test-square' style='background-color: #ff0099;'>T15</span></a>: 2025-04-01 <img src="https://img.shields.io/badge/f1_macro-0.3694170771756979-brightgreen" alt="f1_macro"> <img src="https://img.shields.io/badge/f1_micro-0.3701298701298701-brightgreen" alt="f1_micro"><br><a href='archive/2025-04-01/T16'><span class='test-square' style='background-color: #33ffcc;'>T16</span></a>: 2025-04-01 <img src="https://img.shields.io/badge/f1_macro-0.43630472577841-brightgreen" alt="f1_macro"> <img src="https://img.shields.io/badge/f1_micro-0.43278688524590164-brightgreen" alt="f1_micro"><br><a href='archive/2025-04-01/T17'><span class='test-square' style='background-color: #9b59b6;'>T17</span></a>: 2025-04-01 <img src="https://img.shields.io/badge/f1_macro-0.42966944328105855-brightgreen" alt="f1_macro"> <img src="https://img.shields.io/badge/f1_micro-0.43934426229508194-brightgreen" alt="f1_micro"><br><a href='archive/2025-04-01/T18'><span class='test-square' style='background-color: #99ff33;'>T18</span></a>: 2025-04-01 <img src="https://img.shields.io/badge/f1_macro-0.42007290954659376-brightgreen" alt="f1_macro"> <img src="https://img.shields.io/badge/f1_micro-0.42996742671009774-brightgreen" alt="f1_micro"><br><a href='archive/2025-04-01/T19'><span class='test-square' style='background-color: #0099ff;'>T19</span></a>: 2025-04-01 <img src="https://img.shields.io/badge/f1_macro-0.5612242959703547-brightgreen" alt="f1_macro"> <img src="https://img.shields.io/badge/f1_micro-0.5774647887323944-brightgreen" alt="f1_micro"><br><a href='archive/2025-04-01/T20'><span class='test-square' style='background-color: #ff5050;'>T20</span></a>: 2025-04-01 <img src="https://img.shields.io/badge/f1_macro-0.4940796180052578-brightgreen" alt="f1_macro"> <img src="https://img.shields.io/badge/f1_micro-0.49504950495049505-brightgreen" alt="f1_micro"><br><a href='archive/2025-04-01/T21'><span class='test-square' style='background-color: #9933ff;'>T21</span></a>: 2025-04-01 <img src="https://img.shields.io/badge/f1_macro-0.5516959064327486-brightgreen" alt="f1_macro"> <img src="https://img.shields.io/badge/f1_micro-0.5655172413793104-brightgreen" alt="f1_micro"><br><a href='archive/2025-04-02/T23'><span class='test-square' style='background-color: #ff0066;'>T23</span></a>: 2025-04-02 <img src="https://img.shields.io/badge/f1_macro-0.32800204394481347-brightgreen" alt="f1_macro"> <img src="https://img.shields.io/badge/f1_micro-0.3264094955489614-brightgreen" alt="f1_micro"><br></td>
60+
</tr>
61+
<tr>
62+
<td>fraktur</td>
63+
<td><a href='archive/2025-04-02/T22'><span class='test-square' style='background-color: #2980b9;'>T22</span></a>: 2025-04-02 <img src="https://img.shields.io/badge/score-niy-brightgreen" alt="score"><br></td>
6064
</tr>
6165

6266
</tbody>

docs/tests.md

Lines changed: 23 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -239,7 +239,7 @@ This page provides an overview of all tests. Click on the test name to see the d
239239
<td><span class='test-rectangle' style='background-color: #ff5050;'>anthropic</span></td>
240240
<td><span class='test-rectangle' style='background-color: #cc6699;'>claude-3-5-sonnet-20241022</span></td>
241241
<td>Document</td>
242-
add <td>0.0</td>
242+
<td>0.0</td>
243243
<td>You are a historian with keyword knowledge and an expert in the field of 20th century Swiss history</td>
244244
<td>prompt.txt</td>
245245
<td>false</td>
@@ -277,6 +277,28 @@ add <td>0.0</td>
277277
<td>prompt.txt</td>
278278
<td>false</td>
279279
</tr>
280+
<tr>
281+
<td><a href='tests/T22'><span class='test-square' style='background-color: #2980b9;'>T22</span></a></td>
282+
<td><a href="/benchmarks/fraktur/">fraktur</a></td>
283+
<td><span class='test-rectangle' style='background-color: #ffcc33;'>genai</span></td>
284+
<td><span class='test-rectangle' style='background-color: #e74c3c;'>gemini-2.5-pro-exp-03-25</span></td>
285+
<td></td>
286+
<td>0.0</td>
287+
<td>You are a historian with keyword knowledge and an expert in the field of 20th century Swiss history</td>
288+
<td>prompt.txt</td>
289+
<td>false</td>
290+
</tr>
291+
<tr>
292+
<td><a href='tests/T23'><span class='test-square' style='background-color: #ff0066;'>T23</span></a></td>
293+
<td><a href="/benchmarks/metadata_extraction/">metadata_extraction</a></td>
294+
<td><span class='test-rectangle' style='background-color: #f1c40f;'>mistral</span></td>
295+
<td><span class='test-rectangle' style='background-color: #34495e;'>pixtral-large-latest</span></td>
296+
<td>Document</td>
297+
<td>0.0</td>
298+
<td>You are a historian with keyword knowledge and an expert in the field of 20th century Swiss history. You only return valid JSON an no other text.</td>
299+
<td>prompt.txt</td>
300+
<td>false</td>
301+
</tr>
280302

281303
</tbody>
282304
</table>

mkdocs.yml

Lines changed: 5 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -36,6 +36,8 @@ nav:
3636
- T19: tests/T19.md
3737
- T20: tests/T20.md
3838
- T21: tests/T21.md
39+
- T22: tests/T22.md
40+
- T23: tests/T23.md
3941

4042
- Benchmarks:
4143
- bibliographic_data: benchmarks/bibliographic_data.md
@@ -45,6 +47,9 @@ nav:
4547
- test_benchmark2: benchmarks/test_benchmark2.md
4648
- Archive:
4749
- Overview: archive/overview.md
50+
- 2025-04-02:
51+
- T22: archive/2025-04-02/T22.md
52+
- T23: archive/2025-04-02/T23.md
4853
- 2025-04-01:
4954
- T01: archive/2025-04-01/T01.md
5055
- T02: archive/2025-04-01/T02.md

renders/2025-04-02/T22/image_1.md

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,3 @@
1+
### Result for image: {image_name}
2+
3+
no details available

renders/2025-04-02/T22/image_2.md

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,3 @@
1+
### Result for image: {image_name}
2+
3+
no details available

renders/2025-04-02/T23/letter01.md

Lines changed: 16 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,16 @@
1+
### Result for letter01
2+
| Category | Ground Truth | Prediction | TP | FP | FN |
3+
|------------------|--------------|------------|----|----|----|
4+
| `send_date` | 1926-02-16 | 1926-02-16 | 1 | 0 | 0 |
5+
| `sender_persons` | Groschupf-Jaeger, Louis<br>Ritter-Dreier, Fritz | Herr Dr. Max Vischer<br>Herr Dr. Krasting | 0 | 2 | 2 |
6+
| `receiver_persons` | Christ-Wackernagel, Paul | Herrn Christ<br>Herrn Christ, Paravicini, Christ & Co. | 1 | 1 | 0 |
7+
8+
| Name | Alternate Names |
9+
| --- | --- |
10+
| Groschupf-Jaeger, Louis | Groschopf<br>Groschupf<br>Herr Groschupf<br>Herrn Groschupf |
11+
| Ritter-Dreier, Fritz | Fritz Ritter<br>Herr Fritz Ritter<br>Herr Ritter<br>Herrn Fritz Ritter<br>J.A. Ritter<br>J.A.Ritter<br>Ritter |
12+
| Christ-Wackernagel, Paul | Christ<br>Christ-Wackernagel<br>Herr Christ<br>Herr P. Christ<br>Herr P. Christ - Wackernagel<br>Herr Vice- präsident Christ<br>Herren Christ<br>Herrn Christ<br>Herrn P. Christ<br>Herrn P. Christ - Wackernagel<br>Herrn P. Christ-Wackernagel<br>Herrn Paul Christ<br>Herrn Vizepräsidenten Christ<br>P. Christ - Wackernagel<br>P. Christ-Wackernagel<br>Paul Christ<br>Paul Christ-Wackernagel |
13+
14+
`inferred_from_function`: False
15+
16+
`inferred_from_correspondence`: False

renders/2025-04-02/T23/letter02.md

Lines changed: 15 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,15 @@
1+
### Result for letter02
2+
| Category | Ground Truth | Prediction | TP | FP | FN |
3+
|------------------|--------------|------------|----|----|----|
4+
| `send_date` | 1926-03-04 | 1926-03-04 | 1 | 0 | 0 |
5+
| `sender_persons` | Ritter-Wehrle, Oskar | K.D. Schippang-Aktiengesellschaft<br>C. Rütti | 0 | 2 | 1 |
6+
| `receiver_persons` | Christ-Wackernagel, Paul | Herrn E. Christ<br>Herrn E. Christ - Wassermagel | 0 | 2 | 1 |
7+
8+
| Name | Alternate Names |
9+
| --- | --- |
10+
| Ritter-Wehrle, Oskar | <br>Herren Direktor Ritter<br>O. Ritter |
11+
| Christ-Wackernagel, Paul | Christ<br>Christ-Wackernagel<br>Herr Christ<br>Herr P. Christ<br>Herr P. Christ - Wackernagel<br>Herr Vice- präsident Christ<br>Herren Christ<br>Herrn Christ<br>Herrn P. Christ<br>Herrn P. Christ - Wackernagel<br>Herrn P. Christ-Wackernagel<br>Herrn Paul Christ<br>Herrn Vizepräsidenten Christ<br>P. Christ - Wackernagel<br>P. Christ-Wackernagel<br>Paul Christ<br>Paul Christ-Wackernagel |
12+
13+
`inferred_from_function`: False
14+
15+
`inferred_from_correspondence`: False

renders/2025-04-02/T23/letter03.md

Lines changed: 16 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,16 @@
1+
### Result for letter03
2+
| Category | Ground Truth | Prediction | TP | FP | FN |
3+
|------------------|--------------|------------|----|----|----|
4+
| `send_date` | 1926-03-24 | 1926-03-24 | 1 | 0 | 0 |
5+
| `sender_persons` | Ritter-Dreier, Fritz<br>Kachelhofer-Gerber, Frederick Charles | Basler Rheinschiffahrt-Aktiengesellschaft | 0 | 1 | 2 |
6+
| `receiver_persons` | Christ-Wackernagel, Paul | Herrn P. Christ - Waagarnagel<br>Paravicini, Christ & Co. | 0 | 2 | 1 |
7+
8+
| Name | Alternate Names |
9+
| --- | --- |
10+
| Ritter-Dreier, Fritz | Fritz Ritter<br>Herr Fritz Ritter<br>Herr Ritter<br>Herrn Fritz Ritter<br>J.A. Ritter<br>J.A.Ritter<br>Ritter |
11+
| Kachelhofer-Gerber, Frederick Charles | None |
12+
| Christ-Wackernagel, Paul | Christ<br>Christ-Wackernagel<br>Herr Christ<br>Herr P. Christ<br>Herr P. Christ - Wackernagel<br>Herr Vice- präsident Christ<br>Herren Christ<br>Herrn Christ<br>Herrn P. Christ<br>Herrn P. Christ - Wackernagel<br>Herrn P. Christ-Wackernagel<br>Herrn Paul Christ<br>Herrn Vizepräsidenten Christ<br>P. Christ - Wackernagel<br>P. Christ-Wackernagel<br>Paul Christ<br>Paul Christ-Wackernagel |
13+
14+
`inferred_from_function`: False
15+
16+
`inferred_from_correspondence`: False

renders/2025-04-02/T23/letter04.md

Lines changed: 15 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,15 @@
1+
### Result for letter04
2+
| Category | Ground Truth | Prediction | TP | FP | FN |
3+
|------------------|--------------|------------|----|----|----|
4+
| `send_date` | 1926-03-26 | 1926-03-26 | 1 | 0 | 0 |
5+
| `sender_persons` | Krasting, Wilhelm | W. W. Mann | 0 | 1 | 1 |
6+
| `receiver_persons` | Christ-Wackernagel, Paul | Herr Christ<br>C/O. Faravicini, Christ & Co. | 1 | 1 | 0 |
7+
8+
| Name | Alternate Names |
9+
| --- | --- |
10+
| Krasting, Wilhelm | Dr. Krasting<br>Dr. W. Krasting<br>Herr Dr. Krasting<br>Herrn Dr. Krasting<br>Herrn Dr. W.Krasting |
11+
| Christ-Wackernagel, Paul | Christ<br>Christ-Wackernagel<br>Herr Christ<br>Herr P. Christ<br>Herr P. Christ - Wackernagel<br>Herr Vice- präsident Christ<br>Herren Christ<br>Herrn Christ<br>Herrn P. Christ<br>Herrn P. Christ - Wackernagel<br>Herrn P. Christ-Wackernagel<br>Herrn Paul Christ<br>Herrn Vizepräsidenten Christ<br>P. Christ - Wackernagel<br>P. Christ-Wackernagel<br>Paul Christ<br>Paul Christ-Wackernagel |
12+
13+
`inferred_from_function`: False
14+
15+
`inferred_from_correspondence`: False

0 commit comments

Comments
 (0)