Update README.md

README.md

@@ -174,30 +174,30 @@ Need to install lm-eval from source: https://github.com/EleutherAI/lm-evaluation
 
 ## baseline
 ```Shell
-lm_eval --model hf --model_args pretrained=microsoft/Phi-4-mini-instruct --tasks hellaswag --device cuda:0 --batch_size auto
+lm_eval --model hf --model_args pretrained=Qwen3/Qwen3-4B --tasks hellaswag --device cuda:0 --batch_size auto
 ```
 
 ## int8 dynamic activation and int4 weight quantization (8da4w)
 ```Shell
-lm_eval --model hf --model_args pretrained=pytorch/Phi-4-mini-instruct-8da4w --tasks hellaswag --device cuda:0 --batch_size auto
+lm_eval --model hf --model_args pretrained=TODO:ADD LINK --tasks hellaswag --device cuda:0 --batch_size auto
 ```
 
 | Benchmark                        |                |                           |
 |----------------------------------|----------------|---------------------------|
-|                                  | Qwen3-4B       | Qwen3-4B-8da4w | 
+|                                  | Qwen3-4B       | Qwen3-4B-8da4w            | 
 | **Popular aggregated benchmark** |                |                           |
-| mmlu                    |          |                  |
-| mmlu_pro                |         |                  |
-| bbh
+| mmlu                             | 68.38          | 66.74                     |
+| mmlu_pro                         | 49.71          | 46.73                     |
+| bbh                              | 74.86          | 67.47                     |
 | **Reasoning**                    |                |                           |
-| gpqa_main_zeroshot               |   |                   |
-| mgsm_en_cot_en
+| gpqa_main_zeroshot               | 33.93          | 31.03                     |
+| mgsm_en_cot_en                   | 30.40          | 29.20                     |   
 | **Multilingual**                 |                |                           |
-| m_mmlu                   |          |                      |
+| m_mmlu                           | 50.41          | 47.13                     |
 | **Math**                         |                |                           |
-| gsm8k                   |           |                      |
-| leaderboard_math_hard                  |           |                      |
-| **Overall**                      |           |                     |
+| gsm8k                            | 84.76          | 82.87                     |
+| leaderboard_math_hard            | 62.83          | 53.30                     |
+| **Overall**                      | 56.91          | 53.06                     |
 
 
 # Exporting to ExecuTorch