LICENSE
README.md
pyproject.toml
every_eval_ever/__init__.py
every_eval_ever/__main__.py
every_eval_ever/check_duplicate_entries.py
every_eval_ever/cli.py
every_eval_ever/eval_types.py
every_eval_ever/instance_level_types.py
every_eval_ever/json_utils.py
every_eval_ever/post_codegen.py
every_eval_ever/schema.py
every_eval_ever/validate.py
every_eval_ever/validation_core.py
every_eval_ever.egg-info/PKG-INFO
every_eval_ever.egg-info/SOURCES.txt
every_eval_ever.egg-info/dependency_links.txt
every_eval_ever.egg-info/entry_points.txt
every_eval_ever.egg-info/requires.txt
every_eval_ever.egg-info/top_level.txt
every_eval_ever/adapters/README.md
every_eval_ever/adapters/__init__.py
every_eval_ever/adapters/catalog.py
every_eval_ever/adapters/swe_helpers.py
every_eval_ever/adapters/aixamine/__init__.py
every_eval_ever/adapters/aixamine/adapter.py
every_eval_ever/adapters/arc_agi/__init__.py
every_eval_ever/adapters/arc_agi/adapter.py
every_eval_ever/adapters/artificial_analysis/__init__.py
every_eval_ever/adapters/artificial_analysis/adapter.py
every_eval_ever/adapters/benchpress/README.md
every_eval_ever/adapters/benchpress/__init__.py
every_eval_ever/adapters/benchpress/adapter.py
every_eval_ever/adapters/bfcl/__init__.py
every_eval_ever/adapters/bfcl/adapter.py
every_eval_ever/adapters/bountybench/__init__.py
every_eval_ever/adapters/bountybench/adapter.py
every_eval_ever/adapters/cocoabench/__init__.py
every_eval_ever/adapters/cocoabench/adapter.py
every_eval_ever/adapters/exgentic/__init__.py
every_eval_ever/adapters/exgentic/adapter.py
every_eval_ever/adapters/global_mmlu_lite/__init__.py
every_eval_ever/adapters/global_mmlu_lite/adapter.py
every_eval_ever/adapters/hal/__init__.py
every_eval_ever/adapters/hal/adapter.py
every_eval_ever/adapters/helm/__init__.py
every_eval_ever/adapters/helm/adapter.py
every_eval_ever/adapters/helm/parse_helm_leaderboards.sh
every_eval_ever/adapters/hfopenllm_v2/__init__.py
every_eval_ever/adapters/hfopenllm_v2/adapter.py
every_eval_ever/adapters/hle/__init__.py
every_eval_ever/adapters/hle/adapter.py
every_eval_ever/adapters/lexam/__init__.py
every_eval_ever/adapters/lexam/adapter.py
every_eval_ever/adapters/lexam/refresh_registry_snapshot.py
every_eval_ever/adapters/lexam/registry_snapshot.json
every_eval_ever/adapters/livebench/__init__.py
every_eval_ever/adapters/livebench/adapter.py
every_eval_ever/adapters/livebench/registry_snapshot.json
every_eval_ever/adapters/livecodebenchpro/__init__.py
every_eval_ever/adapters/livecodebenchpro/adapter.py
every_eval_ever/adapters/llm_stats/README.md
every_eval_ever/adapters/llm_stats/__init__.py
every_eval_ever/adapters/llm_stats/adapter.py
every_eval_ever/adapters/mercor_eval/__init__.py
every_eval_ever/adapters/mercor_eval/adapter.py
every_eval_ever/adapters/mmlu_pro/__init__.py
every_eval_ever/adapters/mmlu_pro/adapter.py
every_eval_ever/adapters/mt_bench/__init__.py
every_eval_ever/adapters/mt_bench/adapter.py
every_eval_ever/adapters/multi_swe_bench/__init__.py
every_eval_ever/adapters/multi_swe_bench/adapter.py
every_eval_ever/adapters/open_medical_llm/README.md
every_eval_ever/adapters/open_medical_llm/__init__.py
every_eval_ever/adapters/open_medical_llm/adapter.py
every_eval_ever/adapters/openeval/__init__.py
every_eval_ever/adapters/openeval/adapter.py
every_eval_ever/adapters/paperswithcode/METRIC_MAINTENANCE.md
every_eval_ever/adapters/paperswithcode/__init__.py
every_eval_ever/adapters/paperswithcode/adapter.py
every_eval_ever/adapters/paperswithcode/refresh_registry_snapshot.py
every_eval_ever/adapters/paperswithcode/registry_snapshot.json
every_eval_ever/adapters/paperswithcode_drugbank/__init__.py
every_eval_ever/adapters/paperswithcode_drugbank/adapter.py
every_eval_ever/adapters/rewardbench/__init__.py
every_eval_ever/adapters/rewardbench/adapter.py
every_eval_ever/adapters/rewardbench/migrate_to_v030.py
every_eval_ever/adapters/sciarena/__init__.py
every_eval_ever/adapters/sciarena/adapter.py
every_eval_ever/adapters/swe_bench_verified/__init__.py
every_eval_ever/adapters/swe_bench_verified/adapter.py
every_eval_ever/adapters/swe_polybench/__init__.py
every_eval_ever/adapters/swe_polybench/adapter.py
every_eval_ever/adapters/tau_bench/__init__.py
every_eval_ever/adapters/tau_bench/adapter.py
every_eval_ever/adapters/terminal_bench/__init__.py
every_eval_ever/adapters/terminal_bench/adapter.py
every_eval_ever/adapters/terminal_bench_science/README.md
every_eval_ever/adapters/terminal_bench_science/__init__.py
every_eval_ever/adapters/terminal_bench_science/adapter.py
every_eval_ever/adapters/vals_ai/__init__.py
every_eval_ever/adapters/vals_ai/adapter.py
every_eval_ever/adapters/vectara_hallucination_leaderboard/__init__.py
every_eval_ever/adapters/vectara_hallucination_leaderboard/adapter.py
every_eval_ever/adapters/wild/README.md
every_eval_ever/adapters/wild/__init__.py
every_eval_ever/adapters/wild/adapter.py
every_eval_ever/converters/__init__.py
every_eval_ever/converters/alpaca_eval/__init__.py
every_eval_ever/converters/alpaca_eval/__main__.py
every_eval_ever/converters/alpaca_eval/adapter.py
every_eval_ever/converters/alpaca_eval/identity.py
every_eval_ever/converters/alpaca_eval/refresh_hf_canonical_ids.py
every_eval_ever/converters/alpaca_eval/upstream.py
every_eval_ever/converters/alpaca_eval/data/hf_canonical_ids.json
every_eval_ever/converters/common/__init__.py
every_eval_ever/converters/common/adapter.py
every_eval_ever/converters/common/error.py
every_eval_ever/converters/common/metrics.py
every_eval_ever/converters/common/publication.py
every_eval_ever/converters/common/utils.py
every_eval_ever/converters/helm/__init__.py
every_eval_ever/converters/helm/__main__.py
every_eval_ever/converters/helm/adapter.py
every_eval_ever/converters/helm/instance_level_adapter.py
every_eval_ever/converters/helm/metrics.py
every_eval_ever/converters/helm/utils.py
every_eval_ever/converters/inspect/__init__.py
every_eval_ever/converters/inspect/__main__.py
every_eval_ever/converters/inspect/adapter.py
every_eval_ever/converters/inspect/instance_level_adapter.py
every_eval_ever/converters/inspect/supplemental_eval_details.py
every_eval_ever/converters/inspect/utils.py
every_eval_ever/converters/lm_eval/__init__.py
every_eval_ever/converters/lm_eval/__main__.py
every_eval_ever/converters/lm_eval/adapter.py
every_eval_ever/converters/lm_eval/instance_level_adapter.py
every_eval_ever/converters/lm_eval/utils.py
every_eval_ever/cron/README.md
every_eval_ever/cron/__init__.py
every_eval_ever/cron/__main__.py
every_eval_ever/cron/flat_acknowledged_conflicts.txt
every_eval_ever/cron/flat_rebuild.py
every_eval_ever/cron/provenance.py
every_eval_ever/cron/runner.py
every_eval_ever/cron/store.py
every_eval_ever/cron/submit.py
every_eval_ever/helpers/__init__.py
every_eval_ever/helpers/developer.py
every_eval_ever/helpers/eee_stats.py
every_eval_ever/helpers/eval_card_registry.py
every_eval_ever/helpers/fetch.py
every_eval_ever/helpers/io.py
every_eval_ever/helpers/raw_capture.py
every_eval_ever/helpers/schema.py
every_eval_ever/helpers/data/eval_card_registry.json
every_eval_ever/schemas/__init__.py
every_eval_ever/schemas/eval.schema.json
every_eval_ever/schemas/instance_level_eval.schema.json
every_eval_ever/tools/README.md
every_eval_ever/tools/__init__.py
every_eval_ever/tools/hf_community_evals.py
every_eval_ever/tools/refresh_eval_card_registry.py
every_eval_ever/validator/__init__.py
every_eval_ever/validator/check_duplicate_entries.py
every_eval_ever/validator/cli.py
every_eval_ever/validator/json_utils.py
every_eval_ever/validator/validate.py
every_eval_ever/validator/validation_core.py
tests/test_active_adapter_publication.py
tests/test_adapter_catalog.py
tests/test_aixamine_adapter.py
tests/test_alpaca_eval_adapter.py
tests/test_arc_agi_adapter.py
tests/test_artificial_analysis_adapter.py
tests/test_benchpress_adapter.py
tests/test_bountybench_adapter.py
tests/test_check_duplicate_entries.py
tests/test_cli_inspect_uuid.py
tests/test_community_evals_converter.py
tests/test_converter_conversion.py
tests/test_converter_metric_bounds.py
tests/test_converter_publication.py
tests/test_cron_cli.py
tests/test_cron_provenance.py
tests/test_cron_runner.py
tests/test_cron_store_and_submit.py
tests/test_developer.py
tests/test_documentation_commands.py
tests/test_eval_card_registry.py
tests/test_exgentic_adapter.py
tests/test_flat_rebuild.py
tests/test_global_mmlu_lite_adapter.py
tests/test_hal_adapter.py
tests/test_helm_adapter.py
tests/test_helm_generation_args.py
tests/test_helm_instance_level_adapter.py
tests/test_helpers_io.py
tests/test_hfopenllm_v2_adapter.py
tests/test_hle_adapter.py
tests/test_inf_serialization.py
tests/test_inspect_adapter.py
tests/test_inspect_edge_cases.py
tests/test_inspect_instance_level_adapter.py
tests/test_inspect_uuid_utils.py
tests/test_io_helpers.py
tests/test_legacy_adapter_migrations.py
tests/test_lexam_adapter.py
tests/test_livebench_adapter.py
tests/test_llm_stats_adapter.py
tests/test_lm_eval_adapter.py
tests/test_local_validate.py
tests/test_mercor_eval_adapter.py
tests/test_mmlu_pro_adapter.py
tests/test_mt_bench_adapter.py
tests/test_multi_swe_bench_adapter.py
tests/test_open_medical_llm_adapter.py
tests/test_openeval_adapter.py
tests/test_packaged_resources.py
tests/test_paperswithcode_adapter.py
tests/test_paperswithcode_drugbank_adapter.py
tests/test_paperswithcode_drugbank_registry_contract.py
tests/test_raw_capture.py
tests/test_rewardbench_adapter.py
tests/test_skill_conversion.py
tests/test_swe_bench_verified_adapter.py
tests/test_swe_polybench_adapter.py
tests/test_tau_bench_adapter.py
tests/test_terminal_bench_adapter.py
tests/test_terminal_bench_science_adapter.py
tests/test_validate.py
tests/test_validation_scope.py
tests/test_vals_ai_adapter.py
tests/test_vectara_hallucination_leaderboard_adapter.py
tests/test_wild_adapter.py