Update README.md
Browse files
README.md
CHANGED
|
@@ -178,20 +178,20 @@ print(tokenizer.decode(output[0]))
|
|
| 178 |
<td align="center">42.4</td>
|
| 179 |
<td align="center">43.0</td>
|
| 180 |
<td align="center">65.4</td>
|
| 181 |
-
<td align="center"><
|
| 182 |
<td align="center">68.9</td>
|
| 183 |
</tr>
|
| 184 |
<tr>
|
| 185 |
<td><strong>Mi:dm 2.0-Mini-inst</strong></td>
|
| 186 |
-
<td align="center"><
|
| 187 |
<td align="center">61.4</td>
|
| 188 |
<td align="center">36.7</td>
|
| 189 |
-
<td align="center"><
|
| 190 |
<td align="center">58.8</td>
|
| 191 |
<td align="center">45.1</td>
|
| 192 |
<td align="center">42.4</td>
|
| 193 |
<td align="center">43.8</td>
|
| 194 |
-
<td align="center"
|
| 195 |
<td align="center"><strong>74.0</strong></td>
|
| 196 |
<td align="center"><strong>73.6</strong></td>
|
| 197 |
</tr>
|
|
@@ -202,17 +202,17 @@ print(tokenizer.decode(output[0]))
|
|
| 202 |
<!-- Large Models -->
|
| 203 |
<tr>
|
| 204 |
<td><strong>Qwen3-14B</strong></td>
|
| 205 |
-
<td align="center"
|
| 206 |
<td align="center">65.7</td>
|
| 207 |
-
<td align="center"
|
| 208 |
<td align="center">68.4</td>
|
| 209 |
<td align="center">64.1</td>
|
| 210 |
-
<td align="center"
|
| 211 |
-
<td align="center"
|
| 212 |
-
<td align="center"
|
| 213 |
<td align="center"><strong>83.6</strong></td>
|
| 214 |
<td align="center">71</td>
|
| 215 |
-
<td align="center"
|
| 216 |
</tr>
|
| 217 |
<tr>
|
| 218 |
<td><strong>Llama-3.1-8B-inst</strong></td>
|
|
@@ -231,15 +231,15 @@ print(tokenizer.decode(output[0]))
|
|
| 231 |
<tr>
|
| 232 |
<td><strong>Exaone-3.5-7.8B-inst</strong></td>
|
| 233 |
<td align="center">71.6</td>
|
| 234 |
-
<td align="center"
|
| 235 |
<td align="center">46.9</td>
|
| 236 |
-
<td align="center"
|
| 237 |
-
<td align="center"
|
| 238 |
<td align="center">52.6</td>
|
| 239 |
<td align="center">45.6</td>
|
| 240 |
<td align="center">49.1</td>
|
| 241 |
<td align="center">69.1</td>
|
| 242 |
-
<td align="center"
|
| 243 |
<td align="center">74.4</td>
|
| 244 |
</tr>
|
| 245 |
<tr>
|
|
@@ -252,7 +252,7 @@ print(tokenizer.decode(output[0]))
|
|
| 252 |
<td align="center"><strong>57.3</strong></td>
|
| 253 |
<td align="center"><strong>58.0</strong></td>
|
| 254 |
<td align="center"><strong>57.7</strong></td>
|
| 255 |
-
<td align="center"
|
| 256 |
<td align="center"><strong>89.7</strong></td>
|
| 257 |
<td align="center"><strong>85.9</strong></td>
|
| 258 |
</tr>
|
|
@@ -296,9 +296,9 @@ print(tokenizer.decode(output[0]))
|
|
| 296 |
<td><strong>Exaone-3.5-2.4B-inst</strong></td>
|
| 297 |
<td align="center">68.7</td>
|
| 298 |
<td align="center"><strong>58.5</strong></td>
|
| 299 |
-
<td align="center"
|
| 300 |
<td align="center">38.0</td>
|
| 301 |
-
<td align="center"
|
| 302 |
<td align="center">60.3</td>
|
| 303 |
<td align="center">64.1</td>
|
| 304 |
<td align="center">7.4</td>
|
|
@@ -312,11 +312,11 @@ print(tokenizer.decode(output[0]))
|
|
| 312 |
<td align="center">80.5</td>
|
| 313 |
<td align="center">42.5</td>
|
| 314 |
<td align="center">61.9</td>
|
| 315 |
-
<td align="center"
|
| 316 |
-
<td align="center"
|
| 317 |
<td align="center"><strong>7.7</strong></td>
|
| 318 |
-
<td align="center"
|
| 319 |
-
<td align="center"
|
| 320 |
</tr>
|
| 321 |
|
| 322 |
<!-- Visual Spacer -->
|
|
@@ -351,9 +351,9 @@ print(tokenizer.decode(output[0]))
|
|
| 351 |
</tr>
|
| 352 |
<tr>
|
| 353 |
<td><strong>Exaone-3.5-7.8B-inst</strong></td>
|
| 354 |
-
<td align="center"
|
| 355 |
-
<td align="center"
|
| 356 |
-
<td align="center"
|
| 357 |
<td align="center">44.0</td>
|
| 358 |
<td align="center">67.2</td>
|
| 359 |
<td align="center">64.6</td>
|
|
@@ -364,16 +364,16 @@ print(tokenizer.decode(output[0]))
|
|
| 364 |
</tr>
|
| 365 |
<tr>
|
| 366 |
<td><strong>Mi:dm 2.0-Base-inst</strong></td>
|
| 367 |
-
<td align="center"
|
| 368 |
-
<td align="center"
|
| 369 |
<td align="center"><strong>95.2</strong></td>
|
| 370 |
<td align="center"><strong>53.0</strong></td>
|
| 371 |
-
<td align="center"
|
| 372 |
-
<td align="center"
|
| 373 |
-
<td align="center"
|
| 374 |
<td align="center"><strong>8.6</strong></td>
|
| 375 |
-
<td align="center"
|
| 376 |
-
<td align="center"
|
| 377 |
</tr>
|
| 378 |
</table>
|
| 379 |
|
|
@@ -410,13 +410,13 @@ print(tokenizer.decode(output[0]))
|
|
| 410 |
<!-- Small Models -->
|
| 411 |
<tr>
|
| 412 |
<td><strong>Qwen3-4B</strong></td>
|
| 413 |
-
<td align="center"
|
| 414 |
<td align="center"><strong>79.0</strong></td>
|
| 415 |
-
<td align="center"><
|
| 416 |
<td align="center"><strong>58.5</strong></td>
|
| 417 |
<td align="center"><strong>59.1</strong></td>
|
| 418 |
<td align="center"><strong>90.4</strong></td>
|
| 419 |
-
<td align="center"
|
| 420 |
<td align="center">-</td>
|
| 421 |
<td align="center"><strong>73.3</strong></td>
|
| 422 |
<td align="center"><strong>73.3</strong></td>
|
|
@@ -428,7 +428,7 @@ print(tokenizer.decode(output[0]))
|
|
| 428 |
<td align="center">28.1</td>
|
| 429 |
<td align="center">49.7</td>
|
| 430 |
<td align="center">41.4</td>
|
| 431 |
-
<td align="center"
|
| 432 |
<td align="center">59.8</td>
|
| 433 |
<td align="center">-</td>
|
| 434 |
<td align="center">59.5</td>
|
|
@@ -437,10 +437,10 @@ print(tokenizer.decode(output[0]))
|
|
| 437 |
<tr>
|
| 438 |
<td><strong>Mi:dm 2.0-Mini-inst</strong></td>
|
| 439 |
<td align="center">73.6</td>
|
| 440 |
-
<td align="center"
|
| 441 |
<td align="center">26.6</td>
|
| 442 |
-
<td align="center"
|
| 443 |
-
<td align="center"
|
| 444 |
<td align="center">83.1</td>
|
| 445 |
<td align="center"><strong>60.9</strong></td>
|
| 446 |
<td align="center">-</td>
|
|
@@ -453,7 +453,7 @@ print(tokenizer.decode(output[0]))
|
|
| 453 |
<!-- Large Models -->
|
| 454 |
<tr>
|
| 455 |
<td><strong>Qwen3-14B</strong></td>
|
| 456 |
-
<td align="center"
|
| 457 |
<td align="center"><strong>83.4</strong></td>
|
| 458 |
<td align="center"><strong>49.8</strong></td>
|
| 459 |
<td align="center"><strong>57.7</strong></td>
|
|
@@ -467,23 +467,23 @@ print(tokenizer.decode(output[0]))
|
|
| 467 |
<tr>
|
| 468 |
<td><strong>Llama-3.1-8B-inst</strong></td>
|
| 469 |
<td align="center">79.9</td>
|
| 470 |
-
<td align="center"
|
| 471 |
<td align="center">21.6</td>
|
| 472 |
<td align="center">50.3</td>
|
| 473 |
<td align="center">44.1</td>
|
| 474 |
<td align="center">81.2</td>
|
| 475 |
<td align="center"><strong>81.8</strong></td>
|
| 476 |
<td align="center">47.6</td>
|
| 477 |
-
<td align="center"
|
| 478 |
-
<td align="center"
|
| 479 |
</tr>
|
| 480 |
<tr>
|
| 481 |
<td><strong>Exaone-3.5-7.8B-inst</strong></td>
|
| 482 |
<td align="center">83.6</td>
|
| 483 |
<td align="center">50.1</td>
|
| 484 |
-
<td align="center"
|
| 485 |
-
<td align="center"
|
| 486 |
-
<td align="center"
|
| 487 |
<td align="center">81.1</td>
|
| 488 |
<td align="center">79.4</td>
|
| 489 |
<td align="center">40.7</td>
|
|
@@ -498,8 +498,8 @@ print(tokenizer.decode(output[0]))
|
|
| 498 |
<td align="center">51.9</td>
|
| 499 |
<td align="center">54.4</td>
|
| 500 |
<td align="center"><strong>91.6</strong></td>
|
| 501 |
-
<td align="center"
|
| 502 |
-
<td align="center"
|
| 503 |
<td align="center">73.7</td>
|
| 504 |
<td align="center">63.5</td>
|
| 505 |
</tr>
|
|
|
|
| 178 |
<td align="center">42.4</td>
|
| 179 |
<td align="center">43.0</td>
|
| 180 |
<td align="center">65.4</td>
|
| 181 |
+
<td align="center"><strong>74.0</strong></td>
|
| 182 |
<td align="center">68.9</td>
|
| 183 |
</tr>
|
| 184 |
<tr>
|
| 185 |
<td><strong>Mi:dm 2.0-Mini-inst</strong></td>
|
| 186 |
+
<td align="center"><strong>66.4</strong></td>
|
| 187 |
<td align="center">61.4</td>
|
| 188 |
<td align="center">36.7</td>
|
| 189 |
+
<td align="center"><strong>70.8</strong></td>
|
| 190 |
<td align="center">58.8</td>
|
| 191 |
<td align="center">45.1</td>
|
| 192 |
<td align="center">42.4</td>
|
| 193 |
<td align="center">43.8</td>
|
| 194 |
+
<td align="center">73.3</td>
|
| 195 |
<td align="center"><strong>74.0</strong></td>
|
| 196 |
<td align="center"><strong>73.6</strong></td>
|
| 197 |
</tr>
|
|
|
|
| 202 |
<!-- Large Models -->
|
| 203 |
<tr>
|
| 204 |
<td><strong>Qwen3-14B</strong></td>
|
| 205 |
+
<td align="center">72.4<</td>
|
| 206 |
<td align="center">65.7</td>
|
| 207 |
+
<td align="center">49.8</td>
|
| 208 |
<td align="center">68.4</td>
|
| 209 |
<td align="center">64.1</td>
|
| 210 |
+
<td align="center">55.4</td>
|
| 211 |
+
<td align="center">54.7</td>
|
| 212 |
+
<td align="center">55.1</td>
|
| 213 |
<td align="center"><strong>83.6</strong></td>
|
| 214 |
<td align="center">71</td>
|
| 215 |
+
<td align="center">77.3</td>
|
| 216 |
</tr>
|
| 217 |
<tr>
|
| 218 |
<td><strong>Llama-3.1-8B-inst</strong></td>
|
|
|
|
| 231 |
<tr>
|
| 232 |
<td><strong>Exaone-3.5-7.8B-inst</strong></td>
|
| 233 |
<td align="center">71.6</td>
|
| 234 |
+
<td align="center">69.3</td>
|
| 235 |
<td align="center">46.9</td>
|
| 236 |
+
<td align="center">72.9</td>
|
| 237 |
+
<td align="center">65.2</td>
|
| 238 |
<td align="center">52.6</td>
|
| 239 |
<td align="center">45.6</td>
|
| 240 |
<td align="center">49.1</td>
|
| 241 |
<td align="center">69.1</td>
|
| 242 |
+
<td align="center">79.6</td>
|
| 243 |
<td align="center">74.4</td>
|
| 244 |
</tr>
|
| 245 |
<tr>
|
|
|
|
| 252 |
<td align="center"><strong>57.3</strong></td>
|
| 253 |
<td align="center"><strong>58.0</strong></td>
|
| 254 |
<td align="center"><strong>57.7</strong></td>
|
| 255 |
+
<td align="center">82</td>
|
| 256 |
<td align="center"><strong>89.7</strong></td>
|
| 257 |
<td align="center"><strong>85.9</strong></td>
|
| 258 |
</tr>
|
|
|
|
| 296 |
<td><strong>Exaone-3.5-2.4B-inst</strong></td>
|
| 297 |
<td align="center">68.7</td>
|
| 298 |
<td align="center"><strong>58.5</strong></td>
|
| 299 |
+
<td align="center">87.2</td>
|
| 300 |
<td align="center">38.0</td>
|
| 301 |
+
<td align="center">62.5</td>
|
| 302 |
<td align="center">60.3</td>
|
| 303 |
<td align="center">64.1</td>
|
| 304 |
<td align="center">7.4</td>
|
|
|
|
| 312 |
<td align="center">80.5</td>
|
| 313 |
<td align="center">42.5</td>
|
| 314 |
<td align="center">61.9</td>
|
| 315 |
+
<td align="center">61.7</td>
|
| 316 |
+
<td align="center">64.5</td>
|
| 317 |
<td align="center"><strong>7.7</strong></td>
|
| 318 |
+
<td align="center">39.9</td>
|
| 319 |
+
<td align="center">37.4</td>
|
| 320 |
</tr>
|
| 321 |
|
| 322 |
<!-- Visual Spacer -->
|
|
|
|
| 351 |
</tr>
|
| 352 |
<tr>
|
| 353 |
<td><strong>Exaone-3.5-7.8B-inst</strong></td>
|
| 354 |
+
<td align="center">73.5</td>
|
| 355 |
+
<td align="center">61.9</td>
|
| 356 |
+
<td align="center">92.0</td>
|
| 357 |
<td align="center">44.0</td>
|
| 358 |
<td align="center">67.2</td>
|
| 359 |
<td align="center">64.6</td>
|
|
|
|
| 364 |
</tr>
|
| 365 |
<tr>
|
| 366 |
<td><strong>Mi:dm 2.0-Base-inst</strong></td>
|
| 367 |
+
<td align="center">86.5</td>
|
| 368 |
+
<td align="center">70.8</td>
|
| 369 |
<td align="center"><strong>95.2</strong></td>
|
| 370 |
<td align="center"><strong>53.0</strong></td>
|
| 371 |
+
<td align="center">76.1</td>
|
| 372 |
+
<td align="center">75.1</td>
|
| 373 |
+
<td align="center">73.0</td>
|
| 374 |
<td align="center"><strong>8.6</strong></td>
|
| 375 |
+
<td align="center">52.9</td>
|
| 376 |
+
<td align="center">44.8</td>
|
| 377 |
</tr>
|
| 378 |
</table>
|
| 379 |
|
|
|
|
| 410 |
<!-- Small Models -->
|
| 411 |
<tr>
|
| 412 |
<td><strong>Qwen3-4B</strong></td>
|
| 413 |
+
<td align="center">79.7</td>
|
| 414 |
<td align="center"><strong>79.0</strong></td>
|
| 415 |
+
<td align="center"><strong>39.8</strong></td>
|
| 416 |
<td align="center"><strong>58.5</strong></td>
|
| 417 |
<td align="center"><strong>59.1</strong></td>
|
| 418 |
<td align="center"><strong>90.4</strong></td>
|
| 419 |
+
<td align="center">62.4</td>
|
| 420 |
<td align="center">-</td>
|
| 421 |
<td align="center"><strong>73.3</strong></td>
|
| 422 |
<td align="center"><strong>73.3</strong></td>
|
|
|
|
| 428 |
<td align="center">28.1</td>
|
| 429 |
<td align="center">49.7</td>
|
| 430 |
<td align="center">41.4</td>
|
| 431 |
+
<td align="center">82.5</td>
|
| 432 |
<td align="center">59.8</td>
|
| 433 |
<td align="center">-</td>
|
| 434 |
<td align="center">59.5</td>
|
|
|
|
| 437 |
<tr>
|
| 438 |
<td><strong>Mi:dm 2.0-Mini-inst</strong></td>
|
| 439 |
<td align="center">73.6</td>
|
| 440 |
+
<td align="center">44.5</td>
|
| 441 |
<td align="center">26.6</td>
|
| 442 |
+
<td align="center">51.7</td>
|
| 443 |
+
<td align="center">40.9</td>
|
| 444 |
<td align="center">83.1</td>
|
| 445 |
<td align="center"><strong>60.9</strong></td>
|
| 446 |
<td align="center">-</td>
|
|
|
|
| 453 |
<!-- Large Models -->
|
| 454 |
<tr>
|
| 455 |
<td><strong>Qwen3-14B</strong></td>
|
| 456 |
+
<td align="center">83.9</td>
|
| 457 |
<td align="center"><strong>83.4</strong></td>
|
| 458 |
<td align="center"><strong>49.8</strong></td>
|
| 459 |
<td align="center"><strong>57.7</strong></td>
|
|
|
|
| 467 |
<tr>
|
| 468 |
<td><strong>Llama-3.1-8B-inst</strong></td>
|
| 469 |
<td align="center">79.9</td>
|
| 470 |
+
<td align="center">60.3</td>
|
| 471 |
<td align="center">21.6</td>
|
| 472 |
<td align="center">50.3</td>
|
| 473 |
<td align="center">44.1</td>
|
| 474 |
<td align="center">81.2</td>
|
| 475 |
<td align="center"><strong>81.8</strong></td>
|
| 476 |
<td align="center">47.6</td>
|
| 477 |
+
<td align="center">70.7</td>
|
| 478 |
+
<td align="center">59.2</td>
|
| 479 |
</tr>
|
| 480 |
<tr>
|
| 481 |
<td><strong>Exaone-3.5-7.8B-inst</strong></td>
|
| 482 |
<td align="center">83.6</td>
|
| 483 |
<td align="center">50.1</td>
|
| 484 |
+
<td align="center">33.1</td>
|
| 485 |
+
<td align="center">51.2</td>
|
| 486 |
+
<td align="center">44.8</td>
|
| 487 |
<td align="center">81.1</td>
|
| 488 |
<td align="center">79.4</td>
|
| 489 |
<td align="center">40.7</td>
|
|
|
|
| 498 |
<td align="center">51.9</td>
|
| 499 |
<td align="center">54.4</td>
|
| 500 |
<td align="center"><strong>91.6</strong></td>
|
| 501 |
+
<td align="center">77.5</td>
|
| 502 |
+
<td align="center">53.3</td>
|
| 503 |
<td align="center">73.7</td>
|
| 504 |
<td align="center">63.5</td>
|
| 505 |
</tr>
|