Update README.md

README.md

@@ -115,10 +115,10 @@ The model will output something like:
 
 ## Evaluation
 
-| Model|Average|[ARC](https://arxiv.org/abs/1803.05457)|[HellaSwag](https://arxiv.org/abs/1905.07830)|[MMLU](https://arxiv.org/abs/2009.03300)|[TruthfulQA](https://arxiv.org/abs/2109.07958)|
-|---|---|---|---|---|---|
-| [Aira-2-774M](https://huggingface.co/nicholasKluge/Aira-2-774M) |34.00|**28.75**|40.80|25.10|**41.33**|
-| GPT-2-large | **34.08** | 25.94 | **45.60** | **26.08** | 38.71 |
+| Model|Average|[ARC](https://arxiv.org/abs/1803.05457)|[HellaSwag](https://arxiv.org/abs/1905.07830)|[MMLU](https://arxiv.org/abs/2009.03300)|[TruthfulQA](https://arxiv.org/abs/2109.07958)|[ToxiGen](https://arxiv.org/abs/2203.09509)|
+|---|---|---|---|---|---|---|
+| [Aira-2-774M](https://huggingface.co/nicholasKluge/Aira-2-774M) |**38.53**|**28.75**|40.80|25.10|**41.33**|**56.70**|
+| GPT-2-large | 35.43 | 25.94 | **45.60** | **26.08** | 38.71 | 40.85 |
 
 * Evaluations were performed using the [Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) (by [EleutherAI](https://www.eleuther.ai/)). The notebook used to make these evaluations is available in the [this repo](lm_evaluation_harness.ipynb).