diff --git a/README.md b/README.md
index e2b3bbd..ba648aa 100644
--- a/README.md
+++ b/README.md
@@ -34,12 +34,7 @@ For question-answering, Jan-v1 shows a significant performance gain from model s
 
 These benchmarks evaluate the model's conversational and instructional capabilities.
 
-| Benchmark | JanV1 (Ours) | Qwen3-4B-Thinking-2507 | GPT-OSS-20B (High) | GPT-OSS-20B (Low) |
-| :--- | :--- | :--- | :--- | :--- |
-| EQBench | **83.61** | 82.61 | 78.35 | 78.35 |
-| CreativeWriting | **72.08** | 65.74 | 30.23 | 26.38 |
-| IFBench | **Prompt:** 0.3537<br>**Instruction:** 0.3910 | Prompt: 0.4490<br>Instruction: **0.4806** | Prompt: 0.5646<br>Instruction: 0.6000 | Prompt: 0.5034<br>Instruction: 0.5403 |
-| ArenaHardv2 | **25.3** | - | - | - |
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/65713d70f56f9538679e5a56/fX7BTAHaYdohIj4fbrIhM.png)
 
 ## Quick Start