-
Notifications
You must be signed in to change notification settings - Fork 28
Pull requests: GoogleCloudPlatform/evalbench
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[WIP] fix(dea): support local boq evaluation via stubby transport and suppr…
#525
opened Jul 24, 2026 by
minzznguyen
Contributor
Loading…
chore(main): release 1.14.0
autorelease: pending
#523
opened Jul 24, 2026 by
release-please
Bot
Loading…
Fix cache-corrupted token metrics in multi-turn Claude Code eval
#509
opened Jul 21, 2026 by
prernakakkar-google
Collaborator
Loading…
feat: add dataset-quality scoring framework for CUJ datasets
#508
opened Jul 21, 2026 by
omkargaikwad23
Collaborator
Loading…
5 tasks done
feat(scorers): add non_final_output_tokens metric robust to answer-verbosity variance
#495
opened Jul 15, 2026 by
prernakakkar-google
Collaborator
Loading…
Add support for per-prompt execution timeout (prompt_timeout_seconds)
#493
opened Jul 14, 2026 by
graceqi-g
Collaborator
Loading…
Add field to track time to first response and token usages
#492
opened Jul 13, 2026 by
totoleon
Collaborator
Loading…
feat: Improve isolation of agent evaluation CUJs by staging the work_dir to a new tmp directory tree
#462
opened Jun 26, 2026 by
g-lynnzee
Contributor
Loading…
fix: make PYTHONPATH robust across different working directories
#307
opened Apr 6, 2026 by
aseering
Contributor
Loading…
ProTip!
Filter pull requests by the default branch with base:main.