Update README.md

README.md

@@ -150,7 +150,7 @@ evalplus.evaluate \
 
 #### OpenLLM Leaderboard V1 evaluation scores
 
-| Metric                                  | ibm-granite/granite-3.1-8b-instruct             | neuralmagic-ent/granite-3.1-8b-instruct-quantized.w4a16 |
+| Metric                                  | ibm-granite/granite-3.1-8b-instruct             | neuralmagic-ent/granite-3.1-8b-instruct-FP8-dynamic |
 |-----------------------------------------|:---------------------------------:|:-------------------------------------------:|
 | ARC-Challenge (Acc-Norm, 25-shot)       | 66.81                             | 66.81                                      |
 | GSM8K (Strict-Match, 5-shot)            | 64.52                             | 66.64                                       |
@@ -161,8 +161,19 @@ evalplus.evaluate \
 | **Average Score**                       | **70.30**                         | **70.57**                                   |
 | **Recovery**                            | **100.00**                        | **100.39**                                   |
 
+| Metric                                  | ibm-granite/granite-3.1-8b-instruct             | neuralmagic-ent/granite-3.1-8b-instruct-FP8-dynamic |
+|-----------------------------------------|:---------------------------------:|:-------------------------------------------:|
+| IFEval (Inst Level Strict Acc, 0-shot)| 74.10                           | 73.62                                         |
+| BBH (Acc-Norm, 3-shot)            | 53.19                             | 53.26                                         |
+| Math-Hard (Exact-Match, 4-shot)   | 14.77                            | 16.79                                       |
+| GPQA (Acc-Norm, 0-shot)           | 31.76                             | 32.58                                        |
+| MUSR (Acc-Norm, 0-shot)           | 46.01                             | 47.34                                        |
+| MMLU-Pro (Acc, 5-shot)            | 35.81                             | 35.72                                        |
+| **Average Score**                 | **42.61**                         | **43.22**                                    |
+| **Recovery**                      | **100.00**                         | **101.43**                                    |
+
 #### HumanEval pass@1 scores
-| Metric                                  | ibm-granite/granite-3.1-8b-instruct             | neuralmagic-ent/granite-3.1-8b-instruct-quantized.w4a16 |
+| Metric                                  | ibm-granite/granite-3.1-8b-instruct             | neuralmagic-ent/granite-3.1-8b-instruct-FP8-dynamic |
 |-----------------------------------------|:---------------------------------:|:-------------------------------------------:|
 | HumanEval Pass@1                        | 71.00                             |  69.90                                     |