Update README.md

README.md

@@ -40,7 +40,7 @@ For RL stage we setup training with:
 
 ## III. Evaluation Results
 
-Our II-Medical-8B model achieved a 40% score on [HealthBench](https://openai.com/index/healthbench/), a comprehensive open-source benchmark evaluating the performance and safety of large language models in healthcare. This performance is comparable to OpenAI's o1 reasoning model and GPT-4.5, OpenAI's largest and most advanced model to date. We provide a comparison to models available in ChatGPT below.
+Our II-Medical-8B model achieved a 41% score on [HealthBench](https://openai.com/index/healthbench/), a comprehensive open-source benchmark evaluating the performance and safety of large language models in healthcare. This performance is comparable to OpenAI's o1 reasoning model and GPT-4.5, OpenAI's largest and most advanced model to date. We provide a comparison to models available in ChatGPT below.
 
 ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/61f2636488b9b5abbe184a8e/5r2O4MtzffVYfuUZJe5FO.jpeg)
 Detailed result for HealthBench can be found [here](https://huggingface.co/datasets/Intelligent-Internet/OpenAI-HealthBench-II-Medical-8B-GPT-4.1).
@@ -53,28 +53,28 @@ Journal of Medicine,  4 Options  and 5 Options splits from the MedBullets platfo
 | Model                   | MedMC | MedQA | PubMed | MMLU-P | HealthBench | Lancet | MedB-4 | MedB-5 | MedX  | NEJM  | Avg   |
 |--------------------------|-------|-------|--------|--------|------|--------|--------|--------|------|-------|-------|
 | [HuatuoGPT-o1-72B](https://huggingface.co/FreedomIntelligence/HuatuoGPT-o1-72B)         | **76.76** | 88.85 | **79.90**   | 80.46  | 22.73 | 70.87   | 77.27  | 73.05  |23.53 |76.29  | 66.97 |
-| [M1](https://huggingface.co/UCSC-VLAA/m1-7B-23K)                     | 62.54 | 75.81 | 75.80  | 65.86  | 15.51 | 62.62  | 63.64  | 59.74  |19.59 |64.34  | x  |
+| [M1](https://huggingface.co/UCSC-VLAA/m1-7B-23K)                     | 62.54 | 75.81 | 75.80  | 65.86  | 15.51 | 62.62  | 63.64  | 59.74  |19.59 |64.34  | 56.55  |
 | [Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B)                  | 66.53 | 81.38 | 73.9   | 77.85  | 42.27 | 66.26   | 68.83  | 62.66  |19.59 |69.65  | 62.89 |
 | [Qwen3-32B](https://huggingface.co/Qwen/Qwen3-32B)                  | 74.18 | 88.92 | 76.1   | 80.7  | **47.08** | 72.33   | 72.27  | 71.42  |28.04 |76.94  | 68.80 |
 | [MedGemma-27B-IT](https://huggingface.co/google/medgemma-27b-text-it)                  | 73.24 | 87.27 | 70.9   | 80.13  | 46.54| 70.14   | 75.32  | 73.37  |25.55 |76.28  | 67.87 |
 | [II-Medical-8B](https://huggingface.co/Intelligent-Internet/II-Medical-8B)        | 71.57 | 87.90 | 78.7   |**80.46**  | 40.02| 70.38  | 78.25  | 72.07  |25.26 |73.13  |67.77  |
-| [II-Medical-8B-1706](https://huggingface.co/Intelligent-Internet/II-Medical-8B-1706)            | 74.73 | **90.26** | 79.6   | 80.52  | 42.31| 75  | **80.19**  | **76.30**  |**29.51** |79.77  | **70.82**  |
+| [II-Medical-8B-1706](https://huggingface.co/Intelligent-Internet/II-Medical-8B-1706)            | 74.73 | **90.26** | 79.6   | 80.52  | 41.09| 75  | **80.19**  | **76.30**  |**29.51** |79.77  | **70.7**  |
 
 ## IV. Dataset Curation
 
 The training dataset comprises 2.3M samples from the following sources:
 
-### 1. Public Medical Reasoning Datasets (103,031 samples)
-- [General Medical Reasoning](https://huggingface.co/datasets/GeneralReasoning/GeneralThought-430K): 40,544 samples
-- [Medical-R1-Distill-Data](https://huggingface.co/datasets/FreedomIntelligence/Medical-R1-Distill-Data): 22,000 samples
-- [Medical-R1-Distill-Data-Chinese](https://huggingface.co/datasets/FreedomIntelligence/Medical-R1-Distill-Data-Chinese): 17,000 samples
-- [UCSC-VLAA/m23k-tokenized](https://huggingface.co/datasets/UCSC-VLAA/m23k-tokenized): 23,487 samples
+### 1. Public Medical Reasoning Datasets
+- [General Medical Reasoning](https://huggingface.co/datasets/GeneralReasoning/GeneralThought-430K)
+- [Medical-R1-Distill-Data](https://huggingface.co/datasets/FreedomIntelligence/Medical-R1-Distill-Data)
+- [Medical-R1-Distill-Data-Chinese](https://huggingface.co/datasets/FreedomIntelligence/Medical-R1-Distill-Data-Chinese)
+- [UCSC-VLAA/m23k-tokenized](https://huggingface.co/datasets/UCSC-VLAA/m23k-tokenized)
 
 ### 2. Synthetic Medical QA Data with Qwen3-235B-A22B
 Generated from established medical datasets:
-- [MedMcQA](https://huggingface.co/datasets/openlifescienceai/medmcqa) (from openlifescienceai/medmcqa): 183,000 samples
-- [MedQA](https://huggingface.co/datasets/bigbio/med_qa): 10,000 samples
-- [MedReason](https://huggingface.co/datasets/UCSC-VLAA/MedReason): 32,700 samples
+- [MedMcQA](https://huggingface.co/datasets/openlifescienceai/medmcqa)
+- [MedQA](https://huggingface.co/datasets/bigbio/med_qa)
+- [MedReason](https://huggingface.co/datasets/UCSC-VLAA/MedReason)
 
 ### 3. Curated Medical R1 Traces (338,055 samples)
 
@@ -116,7 +116,7 @@ All R1 reasoning traces were processed through a domain-specific pipeline as fol
    - Minimum threshold: Keep only the prompt with more than 3 words.
    - Wait Token Filter: Removed traces with has more than 47 occurrences of "Wait" (97th percentile threshold).
 3. Response Deduplicate
-   - Ngram: 4.
+   - Ngram: 4
    - Jacard Threshold: 0.7
 
 ### Data Decontamination