Update README.md

README.md

@@ -22,7 +22,7 @@ datasets:
 This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the 
 [OpenThoughts2-1M](https://huggingface.co/datasets/open-thoughts/OpenThoughts2-1M) dataset.
 
-The [OpenThinker2-7B](https://huggingface.co/open-thoughts/OpenThinker2-7B) model delivers performance comparable to state-of-the-art 7B models like DeepSeek-R1-Distill-7B, outperforming it on GPQA-D and LCBv2, and having comparable scores on AIME25, AMC23, and MATH500.
+The [OpenThinker2-7B](https://huggingface.co/open-thoughts/OpenThinker2-7B) model is the top 7B open-data reasoning model. It delivers performance comparable to state of the art 7B models like [DeepSeek-R1-Distill-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) across a suite of tasks.
 This model improves upon our previous [OpenThinker-7B](https://huggingface.co/open-thoughts/OpenThinker-7B) model, which was trained on 114k examples from [OpenThoughts-114k](https://huggingface.co/datasets/open-thoughts/open-thoughts-114k).
 The numbers reported in the table below are evaluated with our open-source tool [Evalchemy](https://github.com/mlfoundations/Evalchemy).
 
@@ -39,7 +39,7 @@ The numbers reported in the table below are evaluated with our open-source tool
 This model was trained on the [OpenThoughts2-1M](https://huggingface.co/datasets/open-thoughts/OpenThoughts2-1M) dataset.
 
 The [OpenThoughts2-1M](https://huggingface.co/datasets/open-thoughts/OpenThoughts2-1M) dataset was constructed by augmenting [OpenThoughts-114k](https://huggingface.co/datasets/open-thoughts/open-thoughts-114k) with existing datasets like [OpenR1](https://huggingface.co/open-r1), as well as additional math and code reasoning data.
-We generate the additional math and code data by ablating on various question generation methodologies and sampling from the highest performing ones. 
+We generate the additional math and code data by ablating over 26 different question generation methodologies and sampling from the highest performing ones. 
 
 See the [OpenThoughts2-1M](https://huggingface.co/datasets/open-thoughts/OpenThoughts2-1M) dataset page or our [blog post](https://www.open-thoughts.ai/blog/thinkagain) for additional information.