Update README.md
Browse files
README.md
CHANGED
|
@@ -7,7 +7,7 @@ Reka Flash 3.1 is an update to our Reka Flash 3. It is particularly strong on co
|
|
| 7 |
|
| 8 |
Reka Flash 3.1 was post trained with synthetic and public datasets for supervised finetuning, followed by large-scale reinforcement learning (RLOO) with verifiable rewards. It improves by 10 points on LiveCodeBench v5 (Full set) from Reka Flash 3 due to significant advances in our reinforcement learning stack. For coding related tasks, Reka Flash 3.1 is competitive with models such as Qwen3-32B. o3-mini, and Gemini 2.5 Flash Thinking.
|
| 9 |
|
| 10 |
-
If you want to learn more about how we do RL for Reka Flash 3.1 that results in these improvements, please check out this post.
|
| 11 |
|
| 12 |
|
| 13 |
|
|
|
|
| 7 |
|
| 8 |
Reka Flash 3.1 was post trained with synthetic and public datasets for supervised finetuning, followed by large-scale reinforcement learning (RLOO) with verifiable rewards. It improves by 10 points on LiveCodeBench v5 (Full set) from Reka Flash 3 due to significant advances in our reinforcement learning stack. For coding related tasks, Reka Flash 3.1 is competitive with models such as Qwen3-32B. o3-mini, and Gemini 2.5 Flash Thinking.
|
| 9 |
|
| 10 |
+
If you want to learn more about how we do RL for Reka Flash 3.1 that results in these improvements, please check out [this post](https://reka.ai/news/reinforcement-learning-for-reka-flash-3-1).
|
| 11 |
|
| 12 |
|
| 13 |
|