README.md
evalscope/__init__.py
evalscope/cache.py
evalscope/config.py
evalscope/constants.py
evalscope/run.py
evalscope/run_arena.py
evalscope/run_ms.py
evalscope/summarizer.py
evalscope/version.py
evalscope.egg-info/PKG-INFO
evalscope.egg-info/SOURCES.txt
evalscope.egg-info/dependency_links.txt
evalscope.egg-info/entry_points.txt
evalscope.egg-info/not-zip-safe
evalscope.egg-info/requires.txt
evalscope.egg-info/top_level.txt
evalscope/backend/__init__.py
evalscope/backend/base.py
evalscope/backend/opencompass/__init__.py
evalscope/backend/opencompass/api_meta_template.py
evalscope/backend/opencompass/backend_manager.py
evalscope/backend/opencompass/tasks/__init__.py
evalscope/backend/opencompass/tasks/eval_api.py
evalscope/backend/opencompass/tasks/eval_datasets.py
evalscope/backend/vlm_eval_kit/__init__.py
evalscope/backend/vlm_eval_kit/backend_manager.py
evalscope/benchmarks/__init__.py
evalscope/benchmarks/benchmark.py
evalscope/benchmarks/data_adapter.py
evalscope/benchmarks/arc/__init__.py
evalscope/benchmarks/arc/ai2_arc.py
evalscope/benchmarks/arc/arc_adapter.py
evalscope/benchmarks/bbh/__init__.py
evalscope/benchmarks/bbh/bbh_adapter.py
evalscope/benchmarks/bbh/cot_prompts/boolean_expressions.txt
evalscope/benchmarks/bbh/cot_prompts/causal_judgement.txt
evalscope/benchmarks/bbh/cot_prompts/date_understanding.txt
evalscope/benchmarks/bbh/cot_prompts/disambiguation_qa.txt
evalscope/benchmarks/bbh/cot_prompts/dyck_languages.txt
evalscope/benchmarks/bbh/cot_prompts/formal_fallacies.txt
evalscope/benchmarks/bbh/cot_prompts/geometric_shapes.txt
evalscope/benchmarks/bbh/cot_prompts/hyperbaton.txt
evalscope/benchmarks/bbh/cot_prompts/logical_deduction_five_objects.txt
evalscope/benchmarks/bbh/cot_prompts/logical_deduction_seven_objects.txt
evalscope/benchmarks/bbh/cot_prompts/logical_deduction_three_objects.txt
evalscope/benchmarks/bbh/cot_prompts/movie_recommendation.txt
evalscope/benchmarks/bbh/cot_prompts/multistep_arithmetic_two.txt
evalscope/benchmarks/bbh/cot_prompts/navigate.txt
evalscope/benchmarks/bbh/cot_prompts/object_counting.txt
evalscope/benchmarks/bbh/cot_prompts/penguins_in_a_table.txt
evalscope/benchmarks/bbh/cot_prompts/reasoning_about_colored_objects.txt
evalscope/benchmarks/bbh/cot_prompts/ruin_names.txt
evalscope/benchmarks/bbh/cot_prompts/salient_translation_error_detection.txt
evalscope/benchmarks/bbh/cot_prompts/snarks.txt
evalscope/benchmarks/bbh/cot_prompts/sports_understanding.txt
evalscope/benchmarks/bbh/cot_prompts/temporal_sequences.txt
evalscope/benchmarks/bbh/cot_prompts/tracking_shuffled_objects_five_objects.txt
evalscope/benchmarks/bbh/cot_prompts/tracking_shuffled_objects_seven_objects.txt
evalscope/benchmarks/bbh/cot_prompts/tracking_shuffled_objects_three_objects.txt
evalscope/benchmarks/bbh/cot_prompts/web_of_lies.txt
evalscope/benchmarks/bbh/cot_prompts/word_sorting.txt
evalscope/benchmarks/ceval/__init__.py
evalscope/benchmarks/ceval/ceval_adapter.py
evalscope/benchmarks/ceval/ceval_exam.py
evalscope/benchmarks/cmmlu/__init__.py
evalscope/benchmarks/cmmlu/cmmlu.py
evalscope/benchmarks/cmmlu/cmmlu_adapter.py
evalscope/benchmarks/competition_math/__init__.py
evalscope/benchmarks/competition_math/competition_math.py
evalscope/benchmarks/competition_math/competition_math_adapter.py
evalscope/benchmarks/general_qa/__init__.py
evalscope/benchmarks/general_qa/general_qa_adapter.py
evalscope/benchmarks/gsm8k/__init__.py
evalscope/benchmarks/gsm8k/gsm8k.py
evalscope/benchmarks/gsm8k/gsm8k_adapter.py
evalscope/benchmarks/hellaswag/__init__.py
evalscope/benchmarks/hellaswag/hellaswag.py
evalscope/benchmarks/hellaswag/hellaswag_adapter.py
evalscope/benchmarks/humaneval/__init__.py
evalscope/benchmarks/humaneval/humaneval.py
evalscope/benchmarks/humaneval/humaneval_adapter.py
evalscope/benchmarks/mmlu/__init__.py
evalscope/benchmarks/mmlu/mmlu.py
evalscope/benchmarks/mmlu/mmlu_adapter.py
evalscope/benchmarks/race/__init__.py
evalscope/benchmarks/race/race.py
evalscope/benchmarks/race/race_adapter.py
evalscope/benchmarks/trivia_qa/__init__.py
evalscope/benchmarks/trivia_qa/trivia_qa.py
evalscope/benchmarks/trivia_qa/trivia_qa_adapter.py
evalscope/benchmarks/truthful_qa/__init__.py
evalscope/benchmarks/truthful_qa/truthful_qa.py
evalscope/benchmarks/truthful_qa/truthful_qa_adapter.py
evalscope/cli/__init__.py
evalscope/cli/base.py
evalscope/cli/cli.py
evalscope/cli/start_perf.py
evalscope/cli/start_server.py
evalscope/evaluator/__init__.py
evalscope/evaluator/evaluator.py
evalscope/evaluator/rating_eval.py
evalscope/evaluator/reviewer/__init__.py
evalscope/evaluator/reviewer/auto_reviewer.py
evalscope/metrics/__init__.py
evalscope/metrics/code_metric.py
evalscope/metrics/math_accuracy.py
evalscope/metrics/metrics.py
evalscope/metrics/rouge_metric.py
evalscope/metrics/bundled_rouge_score/__init__.py
evalscope/metrics/bundled_rouge_score/rouge_scorer.py
evalscope/models/__init__.py
evalscope/models/dummy_chat_model.py
evalscope/models/model.py
evalscope/models/model_adapter.py
evalscope/models/openai_model.py
evalscope/models/template.py
evalscope/models/custom/__init__.py
evalscope/models/custom/custom_model.py
evalscope/perf/__init__.py
evalscope/perf/_logging.py
evalscope/perf/api_plugin_base.py
evalscope/perf/custom_api.py
evalscope/perf/dashscope_api.py
evalscope/perf/dataset_plugin_base.py
evalscope/perf/how_to_analysis_result.py
evalscope/perf/http_client.py
evalscope/perf/openai_api.py
evalscope/perf/plugin_registry.py
evalscope/perf/query_parameters.py
evalscope/perf/server_sent_event.py
evalscope/perf/datasets/__init__.py
evalscope/perf/datasets/line_by_line.py
evalscope/perf/datasets/longalpaca_12k.py
evalscope/perf/datasets/openqa.py
evalscope/preprocess/__init__.py
evalscope/preprocess/tokenizers/__init__.py
evalscope/preprocess/tokenizers/gpt2_tokenizer.py
evalscope/registry/__init__.py
evalscope/registry/tasks/arc.yaml
evalscope/registry/tasks/bbh.yaml
evalscope/registry/tasks/bbh_mini.yaml
evalscope/registry/tasks/ceval.yaml
evalscope/registry/tasks/ceval_mini.yaml
evalscope/registry/tasks/cmmlu.yaml
evalscope/registry/tasks/eval_qwen-7b-chat_v100.yaml
evalscope/registry/tasks/general_qa.yaml
evalscope/registry/tasks/gsm8k.yaml
evalscope/registry/tasks/mmlu.yaml
evalscope/registry/tasks/mmlu_mini.yaml
evalscope/third_party/__init__.py
evalscope/third_party/toolbench_static/__init__.py
evalscope/third_party/toolbench_static/eval.py
evalscope/third_party/toolbench_static/infer.py
evalscope/third_party/toolbench_static/toolbench_static.py
evalscope/third_party/toolbench_static/llm/__init__.py
evalscope/third_party/toolbench_static/llm/swift_infer.py
evalscope/tools/__init__.py
evalscope/tools/combine_reports.py
evalscope/tools/gen_mmlu_subject_mapping.py
evalscope/tools/rewrite_eval_results.py
evalscope/utils/__init__.py
evalscope/utils/arena_utils.py
evalscope/utils/completion_parsers.py
evalscope/utils/logger.py
evalscope/utils/task_cfg_parser.py
evalscope/utils/task_utils.py
evalscope/utils/utils.py