v0.3.0
What's Changed
- docs: update CD and PiPI news by @Perry2004 in #138
- feat: inline LLM judge as second scoring stage by @reacher-z in #139
- feat: add --resume flag to batch runner to skip completed jobs by @erenup in #140
- style: ruff format judge.py and run.py (unblocks main + all open PRs) by @reacher-z in #141
- docs: announce ClawBenchV1Trace dataset + add Datasets section by @reacher-z in #142
- Feat/126 support pi coding agent by @Perry2004 in #143
New Contributors
Full Changelog: https://github.com/reacher-z/ClawBench/blob/main/CHANGELOG.md