LICENSE
README.md
pyproject.toml
src/synthbench/__init__.py
src/synthbench/__main__.py
src/synthbench/adapter.py
src/synthbench/anomaly.py
src/synthbench/baseline_floors.py
src/synthbench/baselines.py
src/synthbench/cli.py
src/synthbench/config_id.py
src/synthbench/contamination.py
src/synthbench/findings.py
src/synthbench/holdout.py
src/synthbench/human_distributions.py
src/synthbench/leaderboard.py
src/synthbench/leaderboard_pr.py
src/synthbench/private_holdout.py
src/synthbench/publish.py
src/synthbench/r2_upload.py
src/synthbench/recompute.py
src/synthbench/report.py
src/synthbench/run_hash.py
src/synthbench/run_validity.py
src/synthbench/runner.py
src/synthbench/stats.py
src/synthbench/submission.py
src/synthbench/submission_pr.py
src/synthbench/submit_adapter.py
src/synthbench/suite.py
src/synthbench/topics.py
src/synthbench/user_config.py
src/synthbench/validation.py
src/synthbench/visualize.py
src/synthbench/convergence/__init__.py
src/synthbench/convergence/baseline.py
src/synthbench/convergence/bootstrap.py
src/synthbench/convergence/cli_report.py
src/synthbench/convergence/curves.py
src/synthbench/convergence/real_sampling.py
src/synthbench/convergence/thresholds.py
src/synthbench/datasets/__init__.py
src/synthbench/datasets/base.py
src/synthbench/datasets/eurobarometer.py
src/synthbench/datasets/globalopinionqa.py
src/synthbench/datasets/gss.py
src/synthbench/datasets/michigan.py
src/synthbench/datasets/ntia.py
src/synthbench/datasets/opinionsqa.py
src/synthbench/datasets/pewtech.py
src/synthbench/datasets/policy.py
src/synthbench/datasets/subpop.py
src/synthbench/datasets/wvs.py
src/synthbench/metrics/__init__.py
src/synthbench/metrics/composite.py
src/synthbench/metrics/conditioning.py
src/synthbench/metrics/distributional.py
src/synthbench/metrics/ranking.py
src/synthbench/metrics/refusal.py
src/synthbench/metrics/subgroup.py
src/synthbench/providers/__init__.py
src/synthbench/providers/_parsing.py
src/synthbench/providers/_retry.py
src/synthbench/providers/base.py
src/synthbench/providers/http.py
src/synthbench/providers/majority_baseline.py
src/synthbench/providers/ollama.py
src/synthbench/providers/openrouter.py
src/synthbench/providers/population_baseline.py
src/synthbench/providers/random_baseline.py
src/synthbench/providers/raw_anthropic.py
src/synthbench/providers/raw_gemini.py
src/synthbench/providers/raw_openai.py
src/synthbench/providers/synthpanel.py
src/synthbench/suites/__init__.py
src/synthbench_eval.egg-info/PKG-INFO
src/synthbench_eval.egg-info/SOURCES.txt
src/synthbench_eval.egg-info/dependency_links.txt
src/synthbench_eval.egg-info/entry_points.txt
src/synthbench_eval.egg-info/requires.txt
src/synthbench_eval.egg-info/top_level.txt
tests/test_anomaly.py
tests/test_baseline_floors.py
tests/test_baselines.py
tests/test_cli_run_submit.py
tests/test_cli_submit.py
tests/test_cli_submit_adapter.py
tests/test_config_id.py
tests/test_contamination.py
tests/test_convergence_baseline.py
tests/test_convergence_bootstrap.py
tests/test_datasets_eurobarometer.py
tests/test_datasets_globalopinionqa.py
tests/test_datasets_gss.py
tests/test_datasets_michigan.py
tests/test_datasets_ntia.py
tests/test_datasets_policy.py
tests/test_datasets_wvs.py
tests/test_effort.py
tests/test_findings_drift.py
tests/test_findings_elicitation.py
tests/test_findings_nonresponse.py
tests/test_holdout.py
tests/test_human_distributions.py
tests/test_integration_tokens.py
tests/test_metrics.py
tests/test_microdata.py
tests/test_private_holdout.py
tests/test_provider_parsing.py
tests/test_providers.py
tests/test_publish_config_id_consistency.py
tests/test_publish_cost.py
tests/test_publish_cross_provider_jsd.py
tests/test_publish_demographic_scorecard.py
tests/test_publish_gated_fail_closed.py
tests/test_publish_holdout.py
tests/test_publish_invalid_runs.py
tests/test_publish_normalized.py
tests/test_publish_policy.py
tests/test_publish_questions.py
tests/test_publish_r2_routing.py
tests/test_publish_rehydration.py
tests/test_publish_run_counts.py
tests/test_publish_runnable_ids.py
tests/test_publish_text_rehydration.py
tests/test_publish_topic_metrics.py
tests/test_r2_upload.py
tests/test_recompute_integrity.py
tests/test_report.py
tests/test_run_hash.py
tests/test_run_validity.py
tests/test_runner.py
tests/test_site_dataset_cards.py
tests/test_stats.py
tests/test_stats_golden.py
tests/test_strip_gated_guard.py
tests/test_submission.py
tests/test_submission_pr.py
tests/test_suite.py
tests/test_suites.py
tests/test_suites_novel_products.py
tests/test_topics.py
tests/test_user_config.py
tests/test_validation.py
tests/test_validation_holdout.py
tests/test_validation_stripped.py
tests/test_verify_publish_integrity.py