Update README.md
Browse files
README.md
CHANGED
|
@@ -26,12 +26,12 @@ The Cogito LLMs are instruction tuned generative models (text in/text out). All
|
|
| 26 |
We compare our models against the state of the art size equivalent models in direct mode as well as the reasoning mode. For the direct mode, we compare against Llama / Qwen instruct counterparts. For reasoning, we use Deepseek's R1 distilled counterparts / Qwen's QwQ model.
|
| 27 |
|
| 28 |
<p align="left">
|
| 29 |
-
<img src="images/3b_benchmarks.png" alt="Logo" width="
|
| 30 |
</p>
|
| 31 |
|
| 32 |
**Livebench Global Average:**
|
| 33 |
<p align="left">
|
| 34 |
-
<img src="images/livebench_global_average.png" alt="Logo" width="
|
| 35 |
</p>
|
| 36 |
|
| 37 |
For detailed evaluations, please refer to the [Blog Post](https://www.deepcogito.com/research/cogito-v1-preview).
|
|
|
|
| 26 |
We compare our models against the state of the art size equivalent models in direct mode as well as the reasoning mode. For the direct mode, we compare against Llama / Qwen instruct counterparts. For reasoning, we use Deepseek's R1 distilled counterparts / Qwen's QwQ model.
|
| 27 |
|
| 28 |
<p align="left">
|
| 29 |
+
<img src="images/3b_benchmarks.png" alt="Logo" width="90%">
|
| 30 |
</p>
|
| 31 |
|
| 32 |
**Livebench Global Average:**
|
| 33 |
<p align="left">
|
| 34 |
+
<img src="images/livebench_global_average.png" alt="Logo" width="80%">
|
| 35 |
</p>
|
| 36 |
|
| 37 |
For detailed evaluations, please refer to the [Blog Post](https://www.deepcogito.com/research/cogito-v1-preview).
|