Update model card: remove AIME/HLE results

README.md

@@ -30,8 +30,6 @@ Netis N1 is a 32B-parameter model specialized for **intelligent IT operations (A
 | GPQA Diamond (198)     |         **54.0%** |
 | IFEval (100)           | **87.0% / 91.2%** |
 | GSM8K (1319)           |             91.4% |
-| AIME (90)              |             11.1% |
-| HLE (100)              |              1.0% |
 
 ## How to Evaluate
 
@@ -45,7 +43,7 @@ python -m vllm.entrypoints.openai.api_server \
 # OpenRCA eval (requires OpenRCA Bank dataset)
 python eval_model.py --llm-backend vllm --vllm-base-url http://localhost:6777
 
-# General benchmarks (MMLU-Pro, GPQA, AIME, IFEval)
+# General benchmarks (MMLU-Pro, GPQA, IFEval, GSM8K)
 python eval_multi_model.py --name netis-n1 --url http://localhost:6777 --model netis-n1
 ```