benchkit-cli 0.1.0__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- benchkit/__init__.py +1 -0
- benchkit/_pi_proxy.py +219 -0
- benchkit/answer_key_guard.ts +49 -0
- benchkit/artifacts.py +87 -0
- benchkit/benchmarks/__init__.py +105 -0
- benchkit/benchmarks/aider_polyglot.py +405 -0
- benchkit/benchmarks/arc.py +52 -0
- benchkit/benchmarks/banking77.py +149 -0
- benchkit/benchmarks/base.py +19 -0
- benchkit/benchmarks/boolq.py +49 -0
- benchkit/benchmarks/chartqa.py +133 -0
- benchkit/benchmarks/code_verifier.py +77 -0
- benchkit/benchmarks/downloads.py +166 -0
- benchkit/benchmarks/evalplus.py +288 -0
- benchkit/benchmarks/git_surgery.py +485 -0
- benchkit/benchmarks/gpqa.py +56 -0
- benchkit/benchmarks/gsm8k.py +97 -0
- benchkit/benchmarks/hellaswag.py +49 -0
- benchkit/benchmarks/humaneval.py +103 -0
- benchkit/benchmarks/ifeval.py +56 -0
- benchkit/benchmarks/ifeval_instructions.py +477 -0
- benchkit/benchmarks/mbpp.py +60 -0
- benchkit/benchmarks/mc_arena.py +479 -0
- benchkit/benchmarks/mcq.py +94 -0
- benchkit/benchmarks/medfailbench.py +537 -0
- benchkit/benchmarks/mmlu.py +54 -0
- benchkit/benchmarks/mmlu_pro.py +62 -0
- benchkit/benchmarks/mmvp.py +115 -0
- benchkit/benchmarks/ocrbench.py +96 -0
- benchkit/benchmarks/openbookqa.py +52 -0
- benchkit/benchmarks/patcheval.py +929 -0
- benchkit/benchmarks/piqa.py +52 -0
- benchkit/benchmarks/ruler.py +172 -0
- benchkit/benchmarks/ruler_generator.py +535 -0
- benchkit/benchmarks/sanity.py +174 -0
- benchkit/benchmarks/treejs_arena.py +268 -0
- benchkit/benchmarks/truthfulqa.py +52 -0
- benchkit/benchmarks/utils.py +25 -0
- benchkit/benchmarks/vision.py +230 -0
- benchkit/benchmarks/vstar.py +108 -0
- benchkit/benchmarks/winogrande.py +52 -0
- benchkit/benchmarks/xstest.py +116 -0
- benchkit/browser.py +429 -0
- benchkit/catalog.py +121 -0
- benchkit/cli.py +1000 -0
- benchkit/client.py +1413 -0
- benchkit/controls.py +87 -0
- benchkit/datasets/MMLU_LICENSE.txt +21 -0
- benchkit/datasets/README.md +142 -0
- benchkit/datasets/arc_challenge.jsonl +1172 -0
- benchkit/datasets/banking77.jsonl +3080 -0
- benchkit/datasets/banking77_intents.json +79 -0
- benchkit/datasets/boolq.jsonl +3270 -0
- benchkit/datasets/code_verifier.jsonl +500 -0
- benchkit/datasets/gpqa_diamond.jsonl +198 -0
- benchkit/datasets/gsm8k.jsonl +1319 -0
- benchkit/datasets/hellaswag.jsonl +1000 -0
- benchkit/datasets/humaneval.jsonl +164 -0
- benchkit/datasets/ifeval.jsonl +541 -0
- benchkit/datasets/mbpp.jsonl +500 -0
- benchkit/datasets/mc_blocks_1_20_1.jsonl +1003 -0
- benchkit/datasets/medfailbench_hard30.jsonl +30 -0
- benchkit/datasets/medfailbench_hard30.md +13 -0
- benchkit/datasets/openbookqa.jsonl +500 -0
- benchkit/datasets/piqa.jsonl +1838 -0
- benchkit/datasets/sanity_code.jsonl +6 -0
- benchkit/datasets/truthfulqa.jsonl +817 -0
- benchkit/datasets/winogrande.jsonl +1267 -0
- benchkit/datasets/xstest.csv +451 -0
- benchkit/decision.py +194 -0
- benchkit/demo.py +451 -0
- benchkit/dockerfiles.py +247 -0
- benchkit/engine.py +1270 -0
- benchkit/evaluation.py +195 -0
- benchkit/events.py +141 -0
- benchkit/executor.py +96 -0
- benchkit/git_surgery/backport-release-stack/setup.sh +328 -0
- benchkit/git_surgery/backport-release-stack/verify.sh +119 -0
- benchkit/git_surgery/bisect-the-regression/setup.sh +49 -0
- benchkit/git_surgery/bisect-the-regression/verify.sh +34 -0
- benchkit/git_surgery/rebase-conflict-chain/setup.sh +65 -0
- benchkit/git_surgery/rebase-conflict-chain/verify.sh +43 -0
- benchkit/git_surgery/recover-complex-stash/setup.sh +152 -0
- benchkit/git_surgery/recover-complex-stash/verify.sh +95 -0
- benchkit/git_surgery/recover-lost-work/setup.sh +40 -0
- benchkit/git_surgery/recover-lost-work/verify.sh +36 -0
- benchkit/git_surgery/repair-force-pushed-remote/setup.sh +171 -0
- benchkit/git_surgery/repair-force-pushed-remote/verify.sh +83 -0
- benchkit/git_surgery/revert-merge-with-followups/setup.sh +198 -0
- benchkit/git_surgery/revert-merge-with-followups/verify.sh +98 -0
- benchkit/git_surgery/secret-in-history/README.md +27 -0
- benchkit/git_surgery/secret-in-history/setup.sh +107 -0
- benchkit/git_surgery/secret-in-history/verify.sh +106 -0
- benchkit/git_surgery/split-the-mega-commit/setup.sh +50 -0
- benchkit/git_surgery/split-the-mega-commit/verify.sh +48 -0
- benchkit/git_surgery/untangle-nested-submodules/setup.sh +193 -0
- benchkit/git_surgery/untangle-nested-submodules/verify.sh +90 -0
- benchkit/history.py +474 -0
- benchkit/jobs.py +332 -0
- benchkit/leakage.py +51 -0
- benchkit/looping.py +873 -0
- benchkit/mc_render.py +274 -0
- benchkit/mc_viewer/dist/atlas.png +0 -0
- benchkit/mc_viewer/dist/blockStates.json.gz +0 -0
- benchkit/mc_viewer/dist/version.json +4 -0
- benchkit/mc_viewer/dist/viewer.html +23 -0
- benchkit/mc_viewer/dist/viewer.js +2 -0
- benchkit/mc_viewer/dist/viewer.js.LICENSE.txt +25 -0
- benchkit/mc_viewer/dist/worker.js +2 -0
- benchkit/mc_viewer/dist/worker.js.LICENSE.txt +19 -0
- benchkit/metrics.py +100 -0
- benchkit/ollama.py +60 -0
- benchkit/perf.py +353 -0
- benchkit/perf_report.py +207 -0
- benchkit/perturbations.py +208 -0
- benchkit/pi_agent.py +476 -0
- benchkit/pi_package/package-lock.json +1827 -0
- benchkit/pi_package/package.json +8 -0
- benchkit/report.py +142 -0
- benchkit/report_markdown.py +645 -0
- benchkit/results.py +688 -0
- benchkit/retry.py +163 -0
- benchkit/runner.py +769 -0
- benchkit/sandbox.py +1167 -0
- benchkit/template_check.py +291 -0
- benchkit/templates/arena.html +504 -0
- benchkit/templates/history.html +58 -0
- benchkit/templates/perf.html +509 -0
- benchkit/templates/report.html +769 -0
- benchkit/tui/__init__.py +5 -0
- benchkit/tui/app.py +87 -0
- benchkit/tui/app.tcss +512 -0
- benchkit/tui/formatting.py +84 -0
- benchkit/tui/screens/__init__.py +1 -0
- benchkit/tui/screens/connect.py +191 -0
- benchkit/tui/screens/detail.py +288 -0
- benchkit/tui/screens/help.py +84 -0
- benchkit/tui/screens/modals.py +544 -0
- benchkit/tui/screens/results.py +361 -0
- benchkit/tui/screens/run.py +988 -0
- benchkit/tui/screens/setup.py +733 -0
- benchkit/tui/theme.py +135 -0
- benchkit/tui/widgets.py +120 -0
- benchkit_cli-0.1.0.dist-info/METADATA +294 -0
- benchkit_cli-0.1.0.dist-info/RECORD +149 -0
- benchkit_cli-0.1.0.dist-info/WHEEL +5 -0
- benchkit_cli-0.1.0.dist-info/entry_points.txt +3 -0
- benchkit_cli-0.1.0.dist-info/licenses/LICENSE +201 -0
- benchkit_cli-0.1.0.dist-info/top_level.txt +1 -0
There are too many changes on this page to be displayed.
The amount of changes on this page would crash your brower.
You can still verify the content by downloading the package file manually.