Update README.md

README.md

@@ -7,4 +7,36 @@ sdk: static
 pinned: false
 ---
 
-Edit this `README.md` markdown file to author your organization card.
+Curating the best open reasoning datasets.  A [Bespoke Labs](https://bespokelabs.ai/) and [DataComp](https://www.datacomp.ai/) community effort.
+
+Our first goal is to curate a reasoning dataset to train state of the art small reasoning models that surpass [DeepSeek-R1-Distill-32B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B) and [DeepSeek-R1-Distill-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) on math and code reasoning benchmarks.
+
+## Latest Results
+
+<Table
+  data={{
+    headers: [
+      "Model",
+      "AIME24",
+      "MATH500",
+      "GPQA-D",
+      "LCB Easy",
+      "LCB Med",
+      "LCB Hard"
+    ],
+    rows: [
+      ["Open-Thinker-7B", "26.7", "86", "40.4", "74.2", "31.1", "3.3"],
+      ["Bespoke-Stratos-7B", "20.0", "82.0", "37.8", "71.4", "25.2", "1.6"],
+      ["DeepSeek-R1-Distill-Qwen-7B", "43.3", "89.4", "44.9", "81.3", "42.2", "2.4"],
+      ["gpt-4o-0513", "9.3", "74.6", "49.9", "-", "-", "-"],
+      ["o1-mini", "63.6", "90.0", "60.0", "-", "-", "-"]
+    ]
+  }}
+/>
+
+
+## About us
+
+We are a team of researchers and engineers from Bespoke Labs, Stanford, University of California Berkeley, University of Washington, Juelich Supercomputing Center (JSC), LAION, UCLA, UNC Chapel Hill, and Toyota Research Institute united around building the best datasets (and thus the best models). See our previous works at [datacomp.ai](https://www.datacomp.ai/) and [mlfoundations](https://github.com/mlfoundations).
+
+Open Thoughts is supported by [Bespoke Labs](https://www.bespokelabs.ai/), [Lambda Labs](https://lambdalabs.com/), [NSF IFML](https://www.ifml.institute/), [Juelich Supercomputing Center](https://www.fz-juelich.de/en/ias/jsc), [Toyota Research Institute](https://www.tri.global/).