Update README.md

README.md

@@ -81,6 +81,9 @@ We use [Language Model Evaluation Harness](https://github.com/EleutherAI/lm-eval
 | MMLU   | 67.9 |
 | **Avg.**                  | **53.3** |
 
+This places DiscoLM 120b firmly ahead of gpt-3.5-turbo-0613 as seen on the screenshot of the current (sadly no longer maintained) FastEval CoT leaderboard:
+![FastEval Leaderboard](imgs/cot_leaderboard.png)
+
 ### MTBench
 
 ```json
@@ -100,6 +103,8 @@ We use [Language Model Evaluation Harness](https://github.com/EleutherAI/lm-eval
     "average": 7.95
 }
 ```
+Screenshot of the current FastEval MT Bench leaderboard:
+![FastEval Leaderboard](imgs/mtbench_leaderboard.png)
 
 ## Prompt Format