sora/evalstone
1
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Restore hle in official suite

Browse Source
This commit is contained in:
sora 2026-07-24 03:18:41 +00:00
parent b15d961153
commit 92f9c970e3
1 changed files with 2 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
bash/run.py
View File

@ -148,8 +148,6 @@ SUITES = {
'single': ['openai_mrcr', 'longbench_v2', 'bfcl_v3', 'mmlu', 'cmmlu', 'bbh', 'simple_qa'], 'single': ['openai_mrcr', 'longbench_v2', 'bfcl_v3', 'mmlu', 'cmmlu', 'bbh', 'simple_qa'],
'agent': ['tau2_bench', 'general_fc'], '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': { 'official': {
'multi': ['aime25', 'aime26', 'live_code_bench'], 'multi': ['aime25', 'aime26', 'live_code_bench'],
'single': [ 'single': [