Spaces:

Nomearod
/

agentbench

Running

App Files Files Community

agentbench / agent_bench /evaluation

Ctrl+K

Ctrl+K

4 contributors

History: 34 commits

Nomearod's picture

calibrate(jury): v1.1+v1.1.1 — fix weighting bugs; recency-position paraphrase clause

ab0e054 8 days ago

calibration
rubric: clarify groundedness reference scope (snippets-only) for v1.1 gold (#20) 9 days ago
datasets
feat(goldens): add source_snippets to 8 FastAPI calibration items 10 days ago
judges
calibrate(jury): v1.1+v1.1.1 — fix weighting bugs; recency-position paraphrase clause 8 days ago
rubrics
rubric: clarify groundedness reference scope (snippets-only) for v1.1 gold (#20) 9 days ago
variance
calibrate(jury): v1.1+v1.1.1 — fix weighting bugs; recency-position paraphrase clause 8 days ago
__init__.py

50 Bytes
feat: Day 4 — corpus, ingest script, first 10 golden questions about 2 months ago
harness.py

8.92 kB
fix(types): four mypy errors blocking CI 10 days ago
metrics.py

4.84 kB
refactor(metrics): delete superseded LLM judges (answer_faithfulness etc.) 10 days ago
report.py

9.55 kB
fix(types): four mypy errors blocking CI 10 days ago