Update README.md

README.md

@@ -10,7 +10,9 @@ base_model:
 ---
 # Reverse Text Model Qwen3-0.6B
 
-Simple model that was RL FT for 20 steps / epochs after SFT to reverse text using [prime-rl](https://github.com/PrimeIntellect-ai/prime-rl/) and [reverse-text](https://github.com/PrimeIntellect-ai/prime-environments/tree/main/environments/reverse_text)
+Simple model that was RL FT for 20 steps / epochs after SFT to reverse text using [prime-rl](https://github.com/PrimeIntellect-ai/prime-rl/) and [reverse-text](https://github.com/PrimeIntellect-ai/prime-environments/tree/main/environments/reverse_text). See the improvement in results:
+
+![](comparison.png)
 
 ## Example Prompt & Reward