-
Notifications
You must be signed in to change notification settings - Fork 27
Pull requests: TIGER-AI-Lab/ClawBench
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
feat(judge): answer/rubric judge — primitive for importing rubric benchmarks (re #170/#188/#189/#190)
#259
opened Jul 11, 2026 by
reacher-z
Collaborator
Loading…
test(corpus): guard task-target integrity (non-empty valid-regex url_pattern + no dupes)
#258
opened Jul 11, 2026 by
reacher-z
Collaborator
Loading…
feat(harness): null + random-click baselines — the benchmark floor (closes #245)
#257
opened Jul 10, 2026 by
reacher-z
Collaborator
Loading…
feat(analyze): aggregate batch error-analysis tool (closes #159)
#255
opened Jul 10, 2026 by
reacher-z
Collaborator
Loading…
feat(edgebench): package ClawBench V2 as an EdgeBench/SForge benchmark
#253
opened Jul 9, 2026 by
reacher-z
Collaborator
Loading…
feat: add Steel cloud browser as alternative browser provider
enhancement
New feature or request
good first issue
Good for newcomers
#100
opened Apr 28, 2026 by
nibzard
Loading…
3 of 5 tasks
ProTip!
Follow long discussions with comments:>50.