lzy/sci-gui-agent-benchmark
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: 更新 Jade/VESTA 任务定义 + 最终评测清单

Browse Source 
- Jade: 15个任务JSON更新 (instruction细化 + metadata.steps详细展开)
- VESTA: 10个任务JSON重构 (统一使用NaCl.cif/anatase_TiO2.cif + 步骤重写)
- VESTA: 删除task1, 新增2个CIF数据文件
- 新增 test_final.json (11 jade + 10 vesta = 21 tasks)
- run_proxmox.sh: MODEL→gpt-5.4, MAX_STEPS→35, TEST_META→test_final.json
This commit is contained in:
lizhanyuan
2026-03-11 11:02:26 +08:00
parent d71f1f976d
commit a943c1e961
30 changed files with 318 additions and 243 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
evaluation_examples/test_final.json Normal file
View File

@@ -0,0 +1,27 @@
{
"jade": [
"MDIJade6.5使用手册_task2",
"MDIJade6.5使用手册_task3",
"jade-guide-example_task1",
"jade-guide-example_task4",
"jade-guide-example_task6",
"jade-guide-example_task7",
"jade-guide-example_task8",
"jade-guide-example_task9",
"jade-guide-example_task10",
"jade-guide-example_task11",
"jade-guide-example_task12"
],
"vesta": [
"VESTA_Manual_task2",
"VESTA_Manual_task3",
"VESTA_Manual_task4",
"VESTA_Manual_task5",
"VESTA_Manual_task6",
"VESTA_Manual_task7",
"VESTA_Manual_task8",
"VESTA_Manual_task9",
"VESTA_Manual_task10",
"VESTA_Manual_task11"
]
}