diff --git a/bash/run.py b/bash/run.py
index f41870f..61e9796 100644
--- a/bash/run.py
+++ b/bash/run.py
@@ -151,14 +151,13 @@ SUITES = {
     # 腾讯/官方入库标准对比套件：取各厂商公开对比表的并集，约 11 个 benchmark
     # 注：swe_bench_verified/terminal_bench_v2/browsecomp/tau2_bench 需要额外镜像/工具
     'official': {
-        'multi': [],
+        'multi': ['aime25', 'aime26','live_code_bench'],
         'single': [
-            'aime25', 'aime26',
-            'hle', 'mmlu_pro', 'gpqa_diamond',
-            'longbench_v2', 'live_code_bench', 'swe_bench_verified',
+            'hle', 'mmlu_pro', 'gpqa_diamond','longbench_v2',
+            # 'swe_bench_verified',
         ],
         'agent': [
-            'tau2_bench', 'terminal_bench_v2', 'browsecomp',
+            'tau2_bench'
         ],
     },
 }
diff --git a/myread.md b/myread.md
index be5a666..260996b 100644
--- a/myread.md
+++ b/myread.md
@@ -409,7 +409,7 @@ python bash/run.py --suite full --thinking --folder-name my_exp_v1 --limit none
 | `group1` | 代码 + 数学/推理 | 约 **22h** | 多机组 1 |
 | `group2` | 重知识 | 约 **26h** | 多机组 2 |
 | `group3` | 长文本 + Agent + 知识 | 约 **27h** | 多机组 3 |
-| `official` | `aime25`, `aime26`, `hle`, `mmlu_pro`, `gpqa_diamond`, `longbench_v2`, `live_code_bench`, `swe_bench_verified`, `tau2_bench`, `terminal_bench_v2`, `browsecomp` | 视配置而定 | 腾讯入库标准对比表的并集，约 11 个 benchmark；其中 swe/terminal/browsecomp/tau2 需额外镜像/工具 |
+| `official` | `aime25`, `aime26`, `live_code_bench`, `hle`, `mmlu_pro`, `gpqa_diamond`, `longbench_v2`, `tau2_bench` | 视配置而定 | 腾讯入库标准对比表核心子集；aime/live_code_bench 多次采样，tau2_bench 为 Agent 任务 |
 
 > **分组时间说明**
 >