Update README.md

Added AIME evaluation

README.md

@@ -43,5 +43,10 @@ print(tokenizer.decode(output[0], skip_special_tokens=False))
 ```
 
 ### Evaluation
+#### MathQA
 The model was evaluated on a randomly sampled subset of 1,000 records from the test split of the [Math-QA](https://huggingface.co/datasets/rvv-karma/Math-QA) dataset.
-Math Genius 7B achieved an accuracy of 93.1% in producing the correct final answer under the pass@1 evaluation metric.
+Math Genius 7B achieved an accuracy of 93.1% in producing the correct final answer under the pass@1 evaluation metric.
+
+#### AIME
+Math Genious 7B was evaluated on [90 problems from AIME 22, AIME 23, and AIME 24](https://huggingface.co/datasets/AI-MO/aimo-validation-aime).
+The model has successfully solved 3/90 of the problems.