Image-Text-to-Text
Transformers
Safetensors
GGUF
gemma3
any-to-any
turkish
türkiye
english
ai
lamapi
next
next-x1
efficient
text-generation
open-source
12b
huggingface
large-language-model
llm
causal
transformer
artificial-intelligence
machine-learning
ai-research
natural-language-processing
language
multilingual
multimodal
nlp
finetuned
lightweight
creative
summarization
question-answering
chat
generative-ai
optimized
unsloth
trl
sft
chemistry
code
biology
finance
legal
music
art
state-of-the-art
climate
medical
agent
text-generation-inference
Merge
dense
conversational
Update README.md
Browse files
README.md
CHANGED
|
@@ -163,7 +163,7 @@ This model is ideal for **enterprises, researchers, and organizations** who need
|
|
| 163 |
</thead>
|
| 164 |
<tbody>
|
| 165 |
<tr class="next">
|
| 166 |
-
<td><strong>Next 14B</strong></td>
|
| 167 |
<td><strong>94.6</strong></td>
|
| 168 |
<td><strong>93.2</strong></td>
|
| 169 |
<td><strong>98.8</strong></td>
|
|
@@ -195,58 +195,6 @@ This model is ideal for **enterprises, researchers, and organizations** who need
|
|
| 195 |
|
| 196 |
---
|
| 197 |
|
| 198 |
-
# Next 12B approaches frontier model performance while maintaining efficiency.
|
| 199 |
-
<table>
|
| 200 |
-
<thead>
|
| 201 |
-
<tr>
|
| 202 |
-
<th>Model</th>
|
| 203 |
-
<th>MMLU (5-shot) %</th>
|
| 204 |
-
<th>MMLU-Pro %</th>
|
| 205 |
-
<th>GSM8K %</th>
|
| 206 |
-
<th>MATH %</th>
|
| 207 |
-
</tr>
|
| 208 |
-
</thead>
|
| 209 |
-
<tbody>
|
| 210 |
-
<tr class="next">
|
| 211 |
-
<td data-label="Model">Next Z1</td>
|
| 212 |
-
<td data-label="MMLU (5-shot) %"><strong>97.3</strong></td>
|
| 213 |
-
<td data-label="MMLU-Pro %"><strong>94.2</strong></td>
|
| 214 |
-
<td data-label="GSM8K %">97.7</td>
|
| 215 |
-
<td data-label="MATH %">93.2</td>
|
| 216 |
-
</tr>
|
| 217 |
-
<tr class="next">
|
| 218 |
-
<td data-label="Model">Next 14B (Thinking)</td>
|
| 219 |
-
<td data-label="MMLU (5-shot) %">94.6</td>
|
| 220 |
-
<td data-label="MMLU-Pro %">83.2</td>
|
| 221 |
-
<td data-label="GSM8K %"><strong>98.8</strong></td>
|
| 222 |
-
<td data-label="MATH %">92.7</td>
|
| 223 |
-
</tr>
|
| 224 |
-
<tr class="next">
|
| 225 |
-
<td data-label="Model">Next 12B</td>
|
| 226 |
-
<td data-label="MMLU (5-shot) %">92.7</td>
|
| 227 |
-
<td data-label="MMLU-Pro %">84.4</td>
|
| 228 |
-
<td data-label="GSM8K %">95.3</td>
|
| 229 |
-
<td data-label="MATH %">87.2</td>
|
| 230 |
-
</tr>
|
| 231 |
-
<tr>
|
| 232 |
-
<td data-label="Model">GPT-5</td>
|
| 233 |
-
<td data-label="MMLU (5-shot) %">92.5</td>
|
| 234 |
-
<td data-label="MMLU-Pro %">87.0</td>
|
| 235 |
-
<td data-label="GSM8K %">98.4</td>
|
| 236 |
-
<td data-label="MATH %"><strong>96.0</strong></td>
|
| 237 |
-
</tr>
|
| 238 |
-
<tr>
|
| 239 |
-
<td data-label="Model">Claude Opus 4.1 (Thinking)</td>
|
| 240 |
-
<td data-label="MMLU (5-shot) %">~92.0</td>
|
| 241 |
-
<td data-label="MMLU-Pro %">87.8</td>
|
| 242 |
-
<td data-label="GSM8K %">84.7</td>
|
| 243 |
-
<td data-label="MATH %">95.4</td>
|
| 244 |
-
</tr>
|
| 245 |
-
</tbody>
|
| 246 |
-
</table>
|
| 247 |
-
|
| 248 |
-
---
|
| 249 |
-
|
| 250 |
## 🚀 Installation & Usage
|
| 251 |
|
| 252 |
### Use with vision:
|
|
|
|
| 163 |
</thead>
|
| 164 |
<tbody>
|
| 165 |
<tr class="next">
|
| 166 |
+
<td><strong>Next 14B (Thinking)</strong></td>
|
| 167 |
<td><strong>94.6</strong></td>
|
| 168 |
<td><strong>93.2</strong></td>
|
| 169 |
<td><strong>98.8</strong></td>
|
|
|
|
| 195 |
|
| 196 |
---
|
| 197 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 198 |
## 🚀 Installation & Usage
|
| 199 |
|
| 200 |
### Use with vision:
|