Update README.md

README.md

@@ -47,6 +47,7 @@ Llama3-70B-SteerLM-RM is trained with NVIDIA [NeMo-Aligner](https://github.com/N
 
  | Model  | Type of Model|  Overall | Chat | Chat-Hard | Safety | Reasoning | 
 |:-----------------------------|:----------------|:-----|:----------|:-------|:----------|:-----------------------|
+  | _**Nemotron-4-340B-RM**_  | Trained with Permissive Licensed Data | **92.0**  | 95.8 |   **87.1** | 91.5  | 93.7 | 
   | ArmoRM-Llama3-8B-v0.1 | Trained with GPT4 Generated Data|  90.8 | 96.9     | 76.8  | 92.2 | 97.3  | 
   | Cohere May 2024   | Proprietary LLM |   89.5  | 96.4     | 71.3      | 92.7 | 97.7  | 
   | _**Llama3-70B-SteerLM-RM**_  | Trained with Permissive Licensed Data | 88.8  | 91.3 |   80.3 | **92.8**  | 90.7 | 
@@ -58,7 +59,7 @@ Llama3-70B-SteerLM-RM is trained with NVIDIA [NeMo-Aligner](https://github.com/N
   | Llama3 70B Instruct | Trained with Permissive Licensed Data | 76.0 | 97.6 | 58.9 | 69.2 | 78.5 | 
        
   
-Last updated: 1 Jun 2024
+Last updated: 12 Jun 2024
 
 Note that we only consider the first four categories in RewardBench, because the optional fifth category (Prior Sets) is 
 1. Heavily towards models trained on Anthropic HHH, Anthropic Helpful, OpenAI Summarize and Stanford Human Preferences (constituent datasets for the Prior Sets category) and therefore can be easily gamed (see About page on RewardBench)