pj/messageboardbench
1
0 Fork 0
mirror of https://github.com/priyanshujain/messageboardbench.git synced 2026-10-02 19:17:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

Checkpoint experiments through SWE pilot v2

Browse Source
This commit is contained in:
pj committed 2026-09-15 15:46:10 +05:30
1 parent abacd5c5e1
commit 72d77018d8
845 files changed
+431756 -41
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

scripts/baseline.py
+2 -2
View File
@@ -27,8 +27,8 @@ from inspect_ai import eval as inspect_eval
from impossiblebench import impossible_livecodebench
MODEL = os.environ.get("MBB_MODEL", "openrouter/z-ai/glm-5.3-flash")
LIMIT = int(os.environ.get("MBB_LIMIT", "40"))
CONCURRENCY = int(os.environ.get("MBB_CONCURRENCY", "12"))
LIMIT = int(os.environ.get("MBB_LIMIT", "2"))
CONCURRENCY = int(os.environ.get("MBB_CONCURRENCY", "2"))
# GLM 5.3 Flash is a reasoning model and single calls legitimately run for minutes,
# so the timeout is generous. It is here to stop one genuinely hung request from