LICENSE
README.md
README_PYPI.md
pyproject.toml
beyondbench/__init__.py
beyondbench/__main__.py
beyondbench/py.typed
beyondbench.egg-info/PKG-INFO
beyondbench.egg-info/SOURCES.txt
beyondbench.egg-info/dependency_links.txt
beyondbench.egg-info/entry_points.txt
beyondbench.egg-info/requires.txt
beyondbench.egg-info/top_level.txt
beyondbench/cli/__init__.py
beyondbench/cli/main.py
beyondbench/cli/wizard.py
beyondbench/configs/__init__.py
beyondbench/configs/config_loader.py
beyondbench/configs/debug.yaml
beyondbench/configs/default.yaml
beyondbench/configs/full_evaluation.yaml
beyondbench/configs/model_validator.py
beyondbench/configs/openai_example.yaml
beyondbench/configs/paper_quality.yaml
beyondbench/configs/quick_test.yaml
beyondbench/configs/schema.json
beyondbench/core/__init__.py
beyondbench/core/base_task.py
beyondbench/core/cache.py
beyondbench/core/eval_fingerprint.py
beyondbench/core/evaluation_engine.py
beyondbench/core/fingerprint.py
beyondbench/core/gpu_scheduler.py
beyondbench/core/noise_injector.py
beyondbench/core/parallel_engine.py
beyondbench/core/rephraser.py
beyondbench/core/result_aggregator.py
beyondbench/core/seed_manager.py
beyondbench/core/task_registry.py
beyondbench/dashboard/__init__.py
beyondbench/dashboard/app.py
beyondbench/dashboard/data_bridge.py
beyondbench/eval/__init__.py
beyondbench/eval/baseline.py
beyondbench/eval/regression.py
beyondbench/models/__init__.py
beyondbench/models/model_handler.py
beyondbench/parsers/__init__.py
beyondbench/parsers/absolute_difference_parsing.py
beyondbench/parsers/alternating_sum_parsing.py
beyondbench/parsers/common.py
beyondbench/parsers/comparison_parsing.py
beyondbench/parsers/core.py
beyondbench/parsers/count_greater_than_previous_parsing.py
beyondbench/parsers/count_multiples_parsing.py
beyondbench/parsers/count_negative_parsing.py
beyondbench/parsers/count_palindromic_parsing.py
beyondbench/parsers/count_perfect_squares_parsing.py
beyondbench/parsers/count_unique_parsing.py
beyondbench/parsers/cumulative_sum_parsing.py
beyondbench/parsers/division_parsing.py
beyondbench/parsers/element_frequency_parsing.py
beyondbench/parsers/even_count_parsing.py
beyondbench/parsers/find_maximum_parsing.py
beyondbench/parsers/find_minimum_parsing.py
beyondbench/parsers/harmonic_sequence_parsing.py
beyondbench/parsers/index_of_maximum_parsing.py
beyondbench/parsers/interleave_lists_parsing.py
beyondbench/parsers/list_parsing_helpers.py
beyondbench/parsers/local_maxima_count_parsing.py
beyondbench/parsers/logical_operations_parsing.py
beyondbench/parsers/longest_increasing_subsequence_parsing.py
beyondbench/parsers/matrix_operations_parsing.py
beyondbench/parsers/max_adjacent_difference_parsing.py
beyondbench/parsers/mean_parsing.py
beyondbench/parsers/median_parsing.py
beyondbench/parsers/mode_parsing.py
beyondbench/parsers/model_adapters.py
beyondbench/parsers/moving_average_parsing.py
beyondbench/parsers/multiplication_parsing.py
beyondbench/parsers/number_base_conversion_parsing.py
beyondbench/parsers/odd_count_parsing.py
beyondbench/parsers/parity_check_parsing.py
beyondbench/parsers/range_parsing.py
beyondbench/parsers/reverse_list_parsing.py
beyondbench/parsers/rotate_list_parsing.py
beyondbench/parsers/running_average_parsing.py
beyondbench/parsers/second_maximum_parsing.py
beyondbench/parsers/set_difference_parsing.py
beyondbench/parsers/set_intersection_parsing.py
beyondbench/parsers/settings.py
beyondbench/parsers/sorting_parsing.py
beyondbench/parsers/subtraction_parsing.py
beyondbench/parsers/sum_of_digits_parsing.py
beyondbench/parsers/sum_of_max_indices_parsing.py
beyondbench/parsers/sum_parsing.py
beyondbench/parsers/task_configs.py
beyondbench/parsers/strategies/__init__.py
beyondbench/parsers/strategies/boxed_strategy.py
beyondbench/parsers/strategies/code_block_strategy.py
beyondbench/parsers/strategies/comparison_strategy.py
beyondbench/parsers/strategies/explicit_statement_strategy.py
beyondbench/parsers/strategies/fallback_strategy.py
beyondbench/parsers/strategies/grid_strategy.py
beyondbench/parsers/strategies/json_strategy.py
beyondbench/parsers/strategies/latex_math_strategy.py
beyondbench/parsers/strategies/list_strategy.py
beyondbench/parsers/strategies/sequence_strategy.py
beyondbench/plugins/__init__.py
beyondbench/plugins/discovery.py
beyondbench/plugins/metadata.py
beyondbench/plugins/scaffold.py
beyondbench/prompts/__init__.py
beyondbench/prompts/few_shot_generator.py
beyondbench/prompts/library.py
beyondbench/prompts/task_prompts.py
beyondbench/prompts/template.py
beyondbench/scripts/audit_contamination.py
beyondbench/scripts/collect_parser_corpus.py
beyondbench/scripts/comprehensive_summary.py
beyondbench/scripts/model_comparison.py
beyondbench/scripts/optimize_prompts.py
beyondbench/scripts/stats_aggregator.py
beyondbench/serve/__init__.py
beyondbench/serve/app.py
beyondbench/serve/models.py
beyondbench/tasks/__init__.py
beyondbench/tasks/easy/__init__.py
beyondbench/tasks/easy/absolute_difference_task.py
beyondbench/tasks/easy/alternating_sum_task.py
beyondbench/tasks/easy/comparison_task.py
beyondbench/tasks/easy/count_greater_than_previous_task.py
beyondbench/tasks/easy/count_multiples_task.py
beyondbench/tasks/easy/count_negative_task.py
beyondbench/tasks/easy/count_palindromic_task.py
beyondbench/tasks/easy/count_perfect_squares_task.py
beyondbench/tasks/easy/count_unique_task.py
beyondbench/tasks/easy/cumulative_sum_task.py
beyondbench/tasks/easy/division_task.py
beyondbench/tasks/easy/dot_product_task.py
beyondbench/tasks/easy/element_frequency_task.py
beyondbench/tasks/easy/even_count_task.py
beyondbench/tasks/easy/find_maximum_task.py
beyondbench/tasks/easy/find_minimum_task.py
beyondbench/tasks/easy/index_of_maximum_task.py
beyondbench/tasks/easy/interleave_lists_task.py
beyondbench/tasks/easy/local_maxima_count_task.py
beyondbench/tasks/easy/longest_increasing_subsequence_task.py
beyondbench/tasks/easy/max_adjacent_difference_task.py
beyondbench/tasks/easy/mean_task.py
beyondbench/tasks/easy/median_task.py
beyondbench/tasks/easy/mode_task.py
beyondbench/tasks/easy/moving_average_task.py
beyondbench/tasks/easy/multiplication_task.py
beyondbench/tasks/easy/odd_count_task.py
beyondbench/tasks/easy/parity_check_task.py
beyondbench/tasks/easy/range_task.py
beyondbench/tasks/easy/reverse_list_task.py
beyondbench/tasks/easy/rotate_list_task.py
beyondbench/tasks/easy/running_average_task.py
beyondbench/tasks/easy/second_maximum_task.py
beyondbench/tasks/easy/second_minimum_task.py
beyondbench/tasks/easy/set_difference_task.py
beyondbench/tasks/easy/set_intersection_task.py
beyondbench/tasks/easy/sorting_task.py
beyondbench/tasks/easy/standard_deviation_task.py
beyondbench/tasks/easy/subtraction_task.py
beyondbench/tasks/easy/sum_of_digits_task.py
beyondbench/tasks/easy/sum_of_max_indices_task.py
beyondbench/tasks/easy/sum_task.py
beyondbench/tasks/easy/variance_task.py
beyondbench/tasks/easy/weighted_sum_task.py
beyondbench/tasks/hard/__init__.py
beyondbench/tasks/hard/boolean_sat_task.py
beyondbench/tasks/hard/coin_change_task.py
beyondbench/tasks/hard/constraint_optimization_task.py
beyondbench/tasks/hard/cryptarithmetic_task.py
beyondbench/tasks/hard/edit_distance_task.py
beyondbench/tasks/hard/graph_coloring_task.py
beyondbench/tasks/hard/interval_scheduling_task.py
beyondbench/tasks/hard/knapsack_task.py
beyondbench/tasks/hard/logic_grid_puzzles_task_enhanced.py
beyondbench/tasks/hard/longest_common_subsequence_task.py
beyondbench/tasks/hard/matrix_chain_multiplication_task.py
beyondbench/tasks/hard/minimax_game_task.py
beyondbench/tasks/hard/modular_systems_solver_task.py
beyondbench/tasks/hard/n_queens_task.py
beyondbench/tasks/hard/regex_matching_task.py
beyondbench/tasks/hard/shortest_path_task.py
beyondbench/tasks/hard/sudoku_task.py
beyondbench/tasks/hard/topological_sort_task.py
beyondbench/tasks/hard/tower_hanoi_task.py
beyondbench/tasks/hard/traveling_salesman_task.py
beyondbench/tasks/medium/__init__.py
beyondbench/tasks/medium/algebraic_sequence_task.py
beyondbench/tasks/medium/arithmetic_progression_task.py
beyondbench/tasks/medium/collatz_sequence_task.py
beyondbench/tasks/medium/combinatorics_task.py
beyondbench/tasks/medium/complex_pattern_task.py
beyondbench/tasks/medium/fibonacci_sequence_task.py
beyondbench/tasks/medium/gcd_lcm_task.py
beyondbench/tasks/medium/geometric_sequence_task.py
beyondbench/tasks/medium/harmonic_sequence_task.py
beyondbench/tasks/medium/logical_operations_task.py
beyondbench/tasks/medium/matrix_operations_task.py
beyondbench/tasks/medium/number_base_conversion_task.py
beyondbench/tasks/medium/pattern_completion_task.py
beyondbench/tasks/medium/polynomial_evaluation_task.py
beyondbench/tasks/medium/prime_sequence_task.py
beyondbench/utils/__init__.py
beyondbench/utils/cost_tracker.py
beyondbench/utils/error_handler.py
beyondbench/utils/logging_utils.py
beyondbench/utils/model_profiler.py
beyondbench/utils/parsing.py
beyondbench/utils/parsing_utils.py
beyondbench/utils/report_generator.py
beyondbench/utils/request_logger.py
beyondbench/utils/sequence_parsing_utils.py
beyondbench/utils/shared_utils.py
beyondbench/utils/stats_tracker.py
beyondbench/utils/token_counter.py
beyondbench/utils/visualizer.py
beyondbench/utils/model_profiles/__init__.py
beyondbench/utils/model_profiles/claude-sonnet-4.json
beyondbench/utils/model_profiles/gemini-2.5-flash.json
beyondbench/utils/model_profiles/gemma-2-2b-it.json
beyondbench/utils/model_profiles/gemma-2-9b-it.json
beyondbench/utils/model_profiles/gpt-4o-mini.json
beyondbench/utils/model_profiles/gpt-4o.json
beyondbench/utils/model_profiles/llama-3.2-1b-instruct.json
beyondbench/utils/model_profiles/llama-3.2-3b-instruct.json
beyondbench/utils/model_profiles/mistral-7b-instruct.json
beyondbench/utils/model_profiles/phi-3.5-mini-instruct.json
beyondbench/utils/model_profiles/qwen2.5-0.5b-instruct.json
beyondbench/utils/model_profiles/qwen2.5-1.5b-instruct.json
beyondbench/utils/model_profiles/qwen2.5-3b-instruct.json
beyondbench/utils/model_profiles/qwen2.5-7b-instruct.json
tests/test_baseline.py
tests/test_ci_quality.py
tests/test_cli.py
tests/test_contamination_resistance.py
tests/test_dashboard.py
tests/test_easy_tasks.py
tests/test_evaluation_engine.py
tests/test_imports.py
tests/test_model_handler.py
tests/test_model_profiling.py
tests/test_parallel_engine.py
tests/test_parser_common.py
tests/test_parsing.py
tests/test_plugins.py
tests/test_prompt_engineering.py
tests/test_reproducibility.py
tests/test_task_registry.py
tests/test_unified_parser.py
tests/test_utils.py