Update README.md

README.md

@@ -1,17 +1,15 @@
 ---
 license: apache-2.0
 tags:
-- chemistry
-- biology
-- legal
-- code
-- medical
-- agent
-- reasoning
-- benchmarks
-- powerful
+  - reasoning
+  - chat
+  - coding
+  - math
+  - science
+  - agent
+  - tools
 base_model:
-- meta-llama/Llama-3.2-3B-Instruct
+- OrionLLM/GRM2-3b
 ---
 
 # GRM2
@@ -65,4 +63,4 @@ The GRM2 delivers performance equivalent to larger models, while remaining open,
 |---|---:|---:|---:|---:|---:|---:|---:|
 | OrionLLM/GRM2-3b | **76.9** | **77.92** | **83.8** | **52.21** | **87.40** | **39.0** | 56.5 |
 | Qwen/Qwen3-32B | 55.7 | 57.08 | 68.4 | 38.72 | 75.83 | 8 | 47.90 |
-| OpenAI/o3-mini | 76.4 | N/A | 79.7 | 39.89 | 86.5 | N/A | **65.12** | 
+| OpenAI/o3-mini | 76.4 | N/A | 79.7 | 39.89 | 86.5 | N/A | **65.12** |