LICENSE
README.md
pyproject.toml
src/benchkit/__init__.py
src/benchkit/_pi_proxy.py
src/benchkit/answer_key_guard.ts
src/benchkit/artifacts.py
src/benchkit/browser.py
src/benchkit/catalog.py
src/benchkit/cli.py
src/benchkit/client.py
src/benchkit/config.py
src/benchkit/controls.py
src/benchkit/decision.py
src/benchkit/demo.py
src/benchkit/dockerfiles.py
src/benchkit/engine.py
src/benchkit/evaluation.py
src/benchkit/events.py
src/benchkit/executor.py
src/benchkit/history.py
src/benchkit/jobs.py
src/benchkit/leakage.py
src/benchkit/looping.py
src/benchkit/mc_render.py
src/benchkit/metrics.py
src/benchkit/ollama.py
src/benchkit/perf.py
src/benchkit/perf_report.py
src/benchkit/perturbations.py
src/benchkit/pi_agent.py
src/benchkit/report.py
src/benchkit/report_markdown.py
src/benchkit/results.py
src/benchkit/retry.py
src/benchkit/runner.py
src/benchkit/sandbox.py
src/benchkit/template_check.py
src/benchkit/benchmarks/__init__.py
src/benchkit/benchmarks/aider_polyglot.py
src/benchkit/benchmarks/arc.py
src/benchkit/benchmarks/banking77.py
src/benchkit/benchmarks/base.py
src/benchkit/benchmarks/boolq.py
src/benchkit/benchmarks/chartqa.py
src/benchkit/benchmarks/code_verifier.py
src/benchkit/benchmarks/downloads.py
src/benchkit/benchmarks/evalplus.py
src/benchkit/benchmarks/git_surgery.py
src/benchkit/benchmarks/gpqa.py
src/benchkit/benchmarks/gsm8k.py
src/benchkit/benchmarks/hellaswag.py
src/benchkit/benchmarks/humaneval.py
src/benchkit/benchmarks/ifeval.py
src/benchkit/benchmarks/ifeval_instructions.py
src/benchkit/benchmarks/mbpp.py
src/benchkit/benchmarks/mc_arena.py
src/benchkit/benchmarks/mcq.py
src/benchkit/benchmarks/medfailbench.py
src/benchkit/benchmarks/mmlu.py
src/benchkit/benchmarks/mmlu_pro.py
src/benchkit/benchmarks/mmvp.py
src/benchkit/benchmarks/ocrbench.py
src/benchkit/benchmarks/openbookqa.py
src/benchkit/benchmarks/patcheval.py
src/benchkit/benchmarks/piqa.py
src/benchkit/benchmarks/ruler.py
src/benchkit/benchmarks/ruler_generator.py
src/benchkit/benchmarks/sanity.py
src/benchkit/benchmarks/treejs_arena.py
src/benchkit/benchmarks/truthfulqa.py
src/benchkit/benchmarks/utils.py
src/benchkit/benchmarks/vision.py
src/benchkit/benchmarks/vstar.py
src/benchkit/benchmarks/winogrande.py
src/benchkit/benchmarks/xstest.py
src/benchkit/datasets/MMLU_LICENSE.txt
src/benchkit/datasets/README.md
src/benchkit/datasets/arc_challenge.jsonl
src/benchkit/datasets/banking77.jsonl
src/benchkit/datasets/banking77_intents.json
src/benchkit/datasets/boolq.jsonl
src/benchkit/datasets/code_verifier.jsonl
src/benchkit/datasets/gpqa_diamond.jsonl
src/benchkit/datasets/gsm8k.jsonl
src/benchkit/datasets/hellaswag.jsonl
src/benchkit/datasets/humaneval.jsonl
src/benchkit/datasets/ifeval.jsonl
src/benchkit/datasets/mbpp.jsonl
src/benchkit/datasets/mc_blocks_1_20_1.jsonl
src/benchkit/datasets/medfailbench_hard30.jsonl
src/benchkit/datasets/medfailbench_hard30.md
src/benchkit/datasets/openbookqa.jsonl
src/benchkit/datasets/piqa.jsonl
src/benchkit/datasets/sanity_code.jsonl
src/benchkit/datasets/truthfulqa.jsonl
src/benchkit/datasets/winogrande.jsonl
src/benchkit/datasets/xstest.csv
src/benchkit/git_surgery/backport-release-stack/setup.sh
src/benchkit/git_surgery/backport-release-stack/verify.sh
src/benchkit/git_surgery/bisect-the-regression/setup.sh
src/benchkit/git_surgery/bisect-the-regression/verify.sh
src/benchkit/git_surgery/rebase-conflict-chain/setup.sh
src/benchkit/git_surgery/rebase-conflict-chain/verify.sh
src/benchkit/git_surgery/recover-complex-stash/setup.sh
src/benchkit/git_surgery/recover-complex-stash/verify.sh
src/benchkit/git_surgery/recover-lost-work/setup.sh
src/benchkit/git_surgery/recover-lost-work/verify.sh
src/benchkit/git_surgery/repair-force-pushed-remote/setup.sh
src/benchkit/git_surgery/repair-force-pushed-remote/verify.sh
src/benchkit/git_surgery/revert-merge-with-followups/setup.sh
src/benchkit/git_surgery/revert-merge-with-followups/verify.sh
src/benchkit/git_surgery/secret-in-history/README.md
src/benchkit/git_surgery/secret-in-history/setup.sh
src/benchkit/git_surgery/secret-in-history/verify.sh
src/benchkit/git_surgery/split-the-mega-commit/setup.sh
src/benchkit/git_surgery/split-the-mega-commit/verify.sh
src/benchkit/git_surgery/untangle-nested-submodules/setup.sh
src/benchkit/git_surgery/untangle-nested-submodules/verify.sh
src/benchkit/mc_viewer/dist/atlas.png
src/benchkit/mc_viewer/dist/blockStates.json.gz
src/benchkit/mc_viewer/dist/version.json
src/benchkit/mc_viewer/dist/viewer.html
src/benchkit/mc_viewer/dist/viewer.js
src/benchkit/mc_viewer/dist/viewer.js.LICENSE.txt
src/benchkit/mc_viewer/dist/worker.js
src/benchkit/mc_viewer/dist/worker.js.LICENSE.txt
src/benchkit/pi_package/package-lock.json
src/benchkit/pi_package/package.json
src/benchkit/templates/arena.html
src/benchkit/templates/history.html
src/benchkit/templates/perf.html
src/benchkit/templates/report.html
src/benchkit/tui/__init__.py
src/benchkit/tui/app.py
src/benchkit/tui/app.tcss
src/benchkit/tui/formatting.py
src/benchkit/tui/theme.py
src/benchkit/tui/widgets.py
src/benchkit/tui/screens/__init__.py
src/benchkit/tui/screens/connect.py
src/benchkit/tui/screens/detail.py
src/benchkit/tui/screens/help.py
src/benchkit/tui/screens/modals.py
src/benchkit/tui/screens/results.py
src/benchkit/tui/screens/run.py
src/benchkit/tui/screens/setup.py
src/benchkit_cli.egg-info/PKG-INFO
src/benchkit_cli.egg-info/SOURCES.txt
src/benchkit_cli.egg-info/dependency_links.txt
src/benchkit_cli.egg-info/entry_points.txt
src/benchkit_cli.egg-info/requires.txt
src/benchkit_cli.egg-info/top_level.txt
tests/test_aider_polyglot.py
tests/test_banking77.py
tests/test_code_verifier.py
tests/test_concurrency.py
tests/test_config.py
tests/test_datasets.py
tests/test_decision.py
tests/test_evalplus.py
tests/test_git_surgery.py
tests/test_gsm8k.py
tests/test_history.py
tests/test_humaneval.py
tests/test_looping.py
tests/test_mc_arena.py
tests/test_mcq.py
tests/test_medfailbench.py
tests/test_medfailbench_real_outputs.py
tests/test_medfailbench_real_outputs_escalation.py
tests/test_medfailbench_scoring_distortion.py
tests/test_patcheval.py
tests/test_perturbations.py
tests/test_pi_harness.py
tests/test_repair.py
tests/test_report.py
tests/test_retry.py
tests/test_ruler.py
tests/test_runner.py
tests/test_sanity.py
tests/test_treejs_arena.py
tests/test_unload.py
tests/test_utils.py
tests/test_vision.py
tests/test_xstest.py