Add: accuracy plots

README.md

@@ -49,19 +49,12 @@ Its lightweight architecture enables fast, large-scale extraction of forecasts,
 **prediction-v1.1-base** consistently outperforms larger state-of-the-art LLMs while being deployable at a much lower cost.
 
 <p align="center">
-    <img src="https://huggingface.co/NOSIBLE/prediction-v1.1-base/resolve/main/results.png"/>
+    <img src="https://huggingface.co/NOSIBLE/prediction-v1.1-base/resolve/main/accuracy.png"/>
 <p>
 
-
-| Model            | Validation Set Accuracy (%)|
-| ---------------- | -------------------------- |
-| **NOSIBLE**      | **94.20**                  |
-| GPT-5.1          | 91.10                      |
-| Gemini 3 Pro     | 92.10                      |
-| Grok-4           | 89.70                      |
-| Claude Opus 4.5  | 90.90                      |
-| Llama 4 Maverick | 90.50                      |
-
+<p align="center">
+    <img src="https://huggingface.co/NOSIBLE/prediction-v1.1-base/resolve/main/results.png"/>
+<p>
 
 ## Class token mapping.
 
@@ -296,4 +289,4 @@ If you use this model, please cite it as follows:
   journal = {Hugging Face Repository},
   howpublished = {https://huggingface.co/NOSIBLE/prediction-v1.1-base}
 }
-```
+```