Update README.md

README.md

@@ -29,10 +29,10 @@ Note that Llama 3 is released under the Meta Llama 3 community license, included
 
 We evaluate the model on [RewardBench](https://github.com/allenai/reward-bench):
 
-| Model            | Score | Chat  | Chat Hard | Safety | Reasoning | Prior Sets (0.5 weight) |
-|------------------|-------|-------|-----------|--------|-----------|-------------------------|
-| **[Llama 3 Tulu 2 8b UF RM](https://huggingface.co/allenai/llama-3-tulu-2-8b-uf-mean-rm) (this model)**  | 66.3  | 96.6  |    59.4   |  61.4  |    80.7   |                         |
-| [Llama 3 Tulu 2 70b UF RM](https://huggingface.co/allenai/llama-3-tulu-2-70b-uf-mean-rm) |    65.3   |   89.1    |      52.6     |    64.0    |      88.3     |                         |
+| Model            | Score | Chat  | Chat Hard | Safety | Reasoning |
+|------------------|-------|-------|-----------|--------|-----------|
+| **[Llama 3 Tulu 2 8b UF RM](https://huggingface.co/allenai/llama-3-tulu-2-8b-uf-mean-rm) (this model)**  | 73.6  | 95.3  |    59.2   |  57.9  |    82.1   |
+| [Llama 3 Tulu 2 70b UF RM](https://huggingface.co/allenai/llama-3-tulu-2-70b-uf-mean-rm) |    65.3   |   89.1    |      52.6     |    64.0    |      88.3     |
 
 
 ## Model description