diff --git a/bash/run.py b/bash/run.py index 61e9796..47e342c 100644 --- a/bash/run.py +++ b/bash/run.py @@ -148,12 +148,10 @@ SUITES = { 'single': ['openai_mrcr', 'longbench_v2', 'bfcl_v3', 'mmlu', 'cmmlu', 'bbh', 'simple_qa'], 'agent': ['tau2_bench', 'general_fc'], }, - # 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': ['aime25', 'aime26','live_code_bench'], + 'multi': ['aime25', 'aime26', 'live_code_bench'], 'single': [ - 'hle', 'mmlu_pro', 'gpqa_diamond','longbench_v2', + 'hle', 'mmlu_pro', 'gpqa_diamond', 'longbench_v2', # 'swe_bench_verified', ], 'agent': [