Update README.md

README.md

@@ -18,7 +18,7 @@ language:
 
 
 
-Calibrated with 10 samples of `mmlu_abstract_algebra`, got eval accuracy of 42, while gemma-3-12b-it-INT4 is 41, and bfloat16 baseline is 43
+Calibrated with 30 samples of `mmlu_philosophy`, got eval accuracy of 76.86, while gemma-3-12b-it-INT4 is 75.56, and bfloat16 baseline is 79.10
 
 
 # Inference with vLLM
@@ -219,7 +219,7 @@ We rely on [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-h
 | Benchmark                        |                        |                             |                                 |
 |----------------------------------|------------------------|-----------------------------|---------------------------------|
 |                                  | google/gemma-3-12b-it  | pytorch/gemma-3-12b-it-INT4 | pytorch/gemma-3-12b-it-AWQ-INT4 |
-| professional_law                 | TODO                   | 54.24                       | TODO                            |
+| philosophy                       | 79.10                  |     75.56                   | 76.85                            |
 
 
 <details>