LICENSE
MANIFEST.in
README.md
requirements.txt
setup.cfg
setup.py
evalscope/__init__.py
evalscope/arguments.py
evalscope/config.py
evalscope/constants.py
evalscope/run.py
evalscope/run_arena.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/rag_eval/__init__.py
evalscope/backend/rag_eval/backend_manager.py
evalscope/backend/rag_eval/clip_benchmark/__init__.py
evalscope/backend/rag_eval/clip_benchmark/arguments.py
evalscope/backend/rag_eval/clip_benchmark/dataset_builder.py
evalscope/backend/rag_eval/clip_benchmark/task_template.py
evalscope/backend/rag_eval/clip_benchmark/tasks/__init__.py
evalscope/backend/rag_eval/clip_benchmark/tasks/image_caption.py
evalscope/backend/rag_eval/clip_benchmark/tasks/zeroshot_classification.py
evalscope/backend/rag_eval/clip_benchmark/tasks/zeroshot_retrieval.py
evalscope/backend/rag_eval/clip_benchmark/utils/webdataset_convert.py
evalscope/backend/rag_eval/clip_benchmark/utils/webdatasets.txt
evalscope/backend/rag_eval/cmteb/__init__.py
evalscope/backend/rag_eval/cmteb/arguments.py
evalscope/backend/rag_eval/cmteb/base.py
evalscope/backend/rag_eval/cmteb/task_template.py
evalscope/backend/rag_eval/cmteb/tasks/Classification.py
evalscope/backend/rag_eval/cmteb/tasks/Clustering.py
evalscope/backend/rag_eval/cmteb/tasks/CustomTask.py
evalscope/backend/rag_eval/cmteb/tasks/PairClassification.py
evalscope/backend/rag_eval/cmteb/tasks/Reranking.py
evalscope/backend/rag_eval/cmteb/tasks/Retrieval.py
evalscope/backend/rag_eval/cmteb/tasks/STS.py
evalscope/backend/rag_eval/cmteb/tasks/__init__.py
evalscope/backend/rag_eval/ragas/__init__.py
evalscope/backend/rag_eval/ragas/arguments.py
evalscope/backend/rag_eval/ragas/task_template.py
evalscope/backend/rag_eval/ragas/prompts/persona_prompt.py
evalscope/backend/rag_eval/ragas/tasks/__init__.py
evalscope/backend/rag_eval/ragas/tasks/build_distribution.py
evalscope/backend/rag_eval/ragas/tasks/build_transform.py
evalscope/backend/rag_eval/ragas/tasks/testset_generation.py
evalscope/backend/rag_eval/ragas/tasks/translate_prompt.py
evalscope/backend/rag_eval/utils/__init__.py
evalscope/backend/rag_eval/utils/clip.py
evalscope/backend/rag_eval/utils/embedding.py
evalscope/backend/rag_eval/utils/llm.py
evalscope/backend/rag_eval/utils/tools.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/utils.py
evalscope/benchmarks/aigc/__init__.py
evalscope/benchmarks/aigc/t2i/__init__.py
evalscope/benchmarks/aigc/t2i/base.py
evalscope/benchmarks/aigc/t2i/evalmuse_adapter.py
evalscope/benchmarks/aigc/t2i/genai_bench_adapter.py
evalscope/benchmarks/aigc/t2i/general_t2i_adapter.py
evalscope/benchmarks/aigc/t2i/hpdv2_adapter.py
evalscope/benchmarks/aigc/t2i/tifa_adapter.py
evalscope/benchmarks/aime/__init__.py
evalscope/benchmarks/aime/aime24_adapter.py
evalscope/benchmarks/aime/aime25_adapter.py
evalscope/benchmarks/alpaca_eval/__init__.py
evalscope/benchmarks/alpaca_eval/alpaca_eval_adapter.py
evalscope/benchmarks/arc/__init__.py
evalscope/benchmarks/arc/ai2_arc.py
evalscope/benchmarks/arc/arc_adapter.py
evalscope/benchmarks/arena_hard/__init__.py
evalscope/benchmarks/arena_hard/arena_hard_adapter.py
evalscope/benchmarks/arena_hard/utils.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/chinese_simple_qa/__init__.py
evalscope/benchmarks/chinese_simple_qa/csimple_qa_adapter.py
evalscope/benchmarks/cmmlu/__init__.py
evalscope/benchmarks/cmmlu/cmmlu.py
evalscope/benchmarks/cmmlu/cmmlu_adapter.py
evalscope/benchmarks/cmmlu/samples.jsonl
evalscope/benchmarks/competition_math/__init__.py
evalscope/benchmarks/competition_math/competition_math.py
evalscope/benchmarks/competition_math/competition_math_adapter.py
evalscope/benchmarks/data_collection/__init__.py
evalscope/benchmarks/data_collection/data_collection_adapter.py
evalscope/benchmarks/drop/__init__.py
evalscope/benchmarks/drop/drop_adapter.py
evalscope/benchmarks/drop/utils.py
evalscope/benchmarks/general_mcq/__init__.py
evalscope/benchmarks/general_mcq/general_mcq_adapter.py
evalscope/benchmarks/general_qa/__init__.py
evalscope/benchmarks/general_qa/general_qa_adapter.py
evalscope/benchmarks/gpqa/__init__.py
evalscope/benchmarks/gpqa/chain_of_thought.txt
evalscope/benchmarks/gpqa/gpqa_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/ifeval/__init__.py
evalscope/benchmarks/ifeval/ifeval_adapter.py
evalscope/benchmarks/ifeval/instructions.py
evalscope/benchmarks/ifeval/instructions_registry.py
evalscope/benchmarks/ifeval/instructions_util.py
evalscope/benchmarks/ifeval/utils.py
evalscope/benchmarks/iquiz/__init__.py
evalscope/benchmarks/iquiz/iquiz_adapter.py
evalscope/benchmarks/live_code_bench/__init__.py
evalscope/benchmarks/live_code_bench/evaluate_utils.py
evalscope/benchmarks/live_code_bench/extract_utils.py
evalscope/benchmarks/live_code_bench/live_code_bench_adapter.py
evalscope/benchmarks/live_code_bench/load_utils.py
evalscope/benchmarks/live_code_bench/pass_k_utils.py
evalscope/benchmarks/live_code_bench/prompts.py
evalscope/benchmarks/live_code_bench/testing_util.py
evalscope/benchmarks/maritime_bench/__init__.py
evalscope/benchmarks/maritime_bench/maritime_bench_adapter.py
evalscope/benchmarks/math_500/__init__.py
evalscope/benchmarks/math_500/math_500_adapter.py
evalscope/benchmarks/mmlu/__init__.py
evalscope/benchmarks/mmlu/mmlu.py
evalscope/benchmarks/mmlu/mmlu_adapter.py
evalscope/benchmarks/mmlu/samples.jsonl
evalscope/benchmarks/mmlu_pro/__init__.py
evalscope/benchmarks/mmlu_pro/mmlu_pro_adapter.py
evalscope/benchmarks/mmlu_redux/__init__.py
evalscope/benchmarks/mmlu_redux/mmlu_redux_adapter.py
evalscope/benchmarks/musr/__init__.py
evalscope/benchmarks/musr/musr_adapter.py
evalscope/benchmarks/process_bench/__init__.py
evalscope/benchmarks/process_bench/critique_template.txt
evalscope/benchmarks/process_bench/process_bench_adapter.py
evalscope/benchmarks/race/__init__.py
evalscope/benchmarks/race/race.py
evalscope/benchmarks/race/race_adapter.py
evalscope/benchmarks/race/samples.jsonl
evalscope/benchmarks/simple_qa/__init__.py
evalscope/benchmarks/simple_qa/simple_qa_adapter.py
evalscope/benchmarks/super_gpqa/__init__.py
evalscope/benchmarks/super_gpqa/five_shot_prompt.txt
evalscope/benchmarks/super_gpqa/super_gpqa_adapter.py
evalscope/benchmarks/super_gpqa/utils.py
evalscope/benchmarks/super_gpqa/zero_shot_prompt.txt
evalscope/benchmarks/tool_bench/__init__.py
evalscope/benchmarks/tool_bench/tool_bench_adapter.py
evalscope/benchmarks/tool_bench/utils.py
evalscope/benchmarks/trivia_qa/__init__.py
evalscope/benchmarks/trivia_qa/samples.jsonl
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/benchmarks/winogrande/__init__.py
evalscope/benchmarks/winogrande/winogrande_adapter.py
evalscope/cli/__init__.py
evalscope/cli/base.py
evalscope/cli/cli.py
evalscope/cli/start_app.py
evalscope/cli/start_eval.py
evalscope/cli/start_perf.py
evalscope/cli/start_server.py
evalscope/collections/__init__.py
evalscope/collections/evaluator.py
evalscope/collections/sampler.py
evalscope/collections/schema.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/llm_judge.py
evalscope/metrics/math_parser.py
evalscope/metrics/metrics.py
evalscope/metrics/named_metrics.py
evalscope/metrics/rouge_metric.py
evalscope/metrics/bundled_rouge_score/__init__.py
evalscope/metrics/bundled_rouge_score/rouge_scorer.py
evalscope/metrics/t2v_metrics/__init__.py
evalscope/metrics/t2v_metrics/clipscore.py
evalscope/metrics/t2v_metrics/constants.py
evalscope/metrics/t2v_metrics/itmscore.py
evalscope/metrics/t2v_metrics/score.py
evalscope/metrics/t2v_metrics/vqascore.py
evalscope/metrics/t2v_metrics/models/__init__.py
evalscope/metrics/t2v_metrics/models/model.py
evalscope/metrics/t2v_metrics/models/utils.py
evalscope/metrics/t2v_metrics/models/clipscore_models/__init__.py
evalscope/metrics/t2v_metrics/models/clipscore_models/clip_model.py
evalscope/metrics/t2v_metrics/models/clipscore_models/hpsv2_model.py
evalscope/metrics/t2v_metrics/models/clipscore_models/mps_model.py
evalscope/metrics/t2v_metrics/models/clipscore_models/pickscore_model.py
evalscope/metrics/t2v_metrics/models/clipscore_models/build_mps_model/__init__.py
evalscope/metrics/t2v_metrics/models/clipscore_models/build_mps_model/base_model.py
evalscope/metrics/t2v_metrics/models/clipscore_models/build_mps_model/clip_model.py
evalscope/metrics/t2v_metrics/models/clipscore_models/build_mps_model/cross_modeling.py
evalscope/metrics/t2v_metrics/models/itmscore_models/__init__.py
evalscope/metrics/t2v_metrics/models/itmscore_models/blip2_itm_model.py
evalscope/metrics/t2v_metrics/models/itmscore_models/fga_blip2_model.py
evalscope/metrics/t2v_metrics/models/itmscore_models/image_reward_model.py
evalscope/metrics/t2v_metrics/models/itmscore_models/image_reward/ImageReward.py
evalscope/metrics/t2v_metrics/models/itmscore_models/image_reward/__init__.py
evalscope/metrics/t2v_metrics/models/itmscore_models/image_reward/blip_pretrain.py
evalscope/metrics/t2v_metrics/models/vqascore_models/__init__.py
evalscope/metrics/t2v_metrics/models/vqascore_models/clip_t5_model.py
evalscope/metrics/t2v_metrics/models/vqascore_models/gpt4v_model.py
evalscope/metrics/t2v_metrics/models/vqascore_models/mm_utils.py
evalscope/metrics/t2v_metrics/models/vqascore_models/vqa_model.py
evalscope/metrics/t2v_metrics/models/vqascore_models/clip_t5/__init__.py
evalscope/metrics/t2v_metrics/models/vqascore_models/clip_t5/model/__init__.py
evalscope/metrics/t2v_metrics/models/vqascore_models/clip_t5/model/language_model/clip_t5.py
evalscope/metrics/t2v_metrics/models/vqascore_models/clip_t5/model/multimodal_encoder/builder.py
evalscope/metrics/t2v_metrics/models/vqascore_models/clip_t5/model/multimodal_encoder/clip_encoder.py
evalscope/metrics/t2v_metrics/models/vqascore_models/clip_t5/model/multimodal_projector/builder.py
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/__init__.py
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/config.py
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/dist_utils.py
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/gradcam.py
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/logger.py
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/optims.py
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/registry.py
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/utils.py
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/vqa_tools/__init__.py
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/vqa_tools/vqa.py
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/vqa_tools/vqa_eval.py
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/default.yaml
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/med_config.json
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/med_config_albef.json
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/med_large_config.json
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_caption_flant5xl.yaml
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_caption_opt2.7b.yaml
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_caption_opt6.7b.yaml
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_coco.yaml
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_instruct_flant5xl.yaml
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_instruct_flant5xxl.yaml
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_instruct_vicuna13b.yaml
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_instruct_vicuna7b.yaml
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_pretrain.yaml
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_pretrain_flant5xl.yaml
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_pretrain_flant5xl_iter_80k_total_100k_no_prefix.yaml
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_pretrain_flant5xl_iter_80k_total_100k_prefix.yaml
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_pretrain_flant5xl_vitL.yaml
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_pretrain_flant5xxl.yaml
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_pretrain_opt2.7b.yaml
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_pretrain_opt6.7b.yaml
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_pretrain_vitL.yaml
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_vicuna13b.yaml
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_vicuna7b.yaml
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/__init__.py
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/base_model.py
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/clip_vit.py
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/eva_vit.py
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/med.py
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/vit.py
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/Qformer.py
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/__init__.py
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/blip2.py
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/blip2_image_text_matching.py
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/blip2_qformer.py
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/blip2_t5.py
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/blip2_t5_instruct.py
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/fga_blip2.py
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/modeling_llama.py
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/modeling_t5.py
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/__init__.py
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip.py
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip_caption.py
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip_classification.py
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip_feature_extractor.py
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip_image_text_matching.py
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip_nlvr.py
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip_outputs.py
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip_pretrain.py
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip_vqa.py
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/nlvr_encoder.py
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/processors/__init__.py
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/processors/base_processor.py
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/processors/blip_processors.py
evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/processors/randaugment.py
evalscope/models/__init__.py
evalscope/models/local_model.py
evalscope/models/model.py
evalscope/models/register.py
evalscope/models/adapters/__init__.py
evalscope/models/adapters/base_adapter.py
evalscope/models/adapters/chat_adapter.py
evalscope/models/adapters/choice_adapter.py
evalscope/models/adapters/custom_adapter.py
evalscope/models/adapters/server_adapter.py
evalscope/models/adapters/t2i_adapter.py
evalscope/models/custom/__init__.py
evalscope/models/custom/custom_model.py
evalscope/models/custom/dummy_model.py
evalscope/perf/__init__.py
evalscope/perf/arguments.py
evalscope/perf/benchmark.py
evalscope/perf/http_client.py
evalscope/perf/main.py
evalscope/perf/plugin/__init__.py
evalscope/perf/plugin/registry.py
evalscope/perf/plugin/api/__init__.py
evalscope/perf/plugin/api/base.py
evalscope/perf/plugin/api/custom_api.py
evalscope/perf/plugin/api/dashscope_api.py
evalscope/perf/plugin/api/openai_api.py
evalscope/perf/plugin/datasets/__init__.py
evalscope/perf/plugin/datasets/base.py
evalscope/perf/plugin/datasets/custom.py
evalscope/perf/plugin/datasets/flickr8k.py
evalscope/perf/plugin/datasets/line_by_line.py
evalscope/perf/plugin/datasets/longalpaca.py
evalscope/perf/plugin/datasets/openqa.py
evalscope/perf/plugin/datasets/random_dataset.py
evalscope/perf/plugin/datasets/speed_benchmark.py
evalscope/perf/utils/__init__.py
evalscope/perf/utils/analysis_result.py
evalscope/perf/utils/benchmark_util.py
evalscope/perf/utils/db_util.py
evalscope/perf/utils/handler.py
evalscope/perf/utils/local_server.py
evalscope/perf/utils/log_utils.py
evalscope/perf/utils/rich_display.py
evalscope/registry/__init__.py
evalscope/registry/config/cfg_arena.yaml
evalscope/registry/config/cfg_arena_zhihu.yaml
evalscope/registry/config/cfg_pairwise_baseline.yaml
evalscope/registry/config/cfg_single.yaml
evalscope/registry/data/question.jsonl
evalscope/registry/data/prompt_template/lmsys_v2.jsonl
evalscope/registry/data/prompt_template/prompt_templates.jsonl
evalscope/registry/data/qa_browser/battle.jsonl
evalscope/registry/data/qa_browser/category_mapping.yaml
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/report/__init__.py
evalscope/report/app.py
evalscope/report/app_arguments.py
evalscope/report/combinator.py
evalscope/report/generator.py
evalscope/report/utils.py
evalscope/third_party/__init__.py
evalscope/third_party/longbench_write/README.md
evalscope/third_party/longbench_write/__init__.py
evalscope/third_party/longbench_write/default_task.json
evalscope/third_party/longbench_write/default_task.yaml
evalscope/third_party/longbench_write/eval.py
evalscope/third_party/longbench_write/infer.py
evalscope/third_party/longbench_write/longbench_write.py
evalscope/third_party/longbench_write/utils.py
evalscope/third_party/longbench_write/resources/__init__.py
evalscope/third_party/longbench_write/resources/judge.txt
evalscope/third_party/longbench_write/resources/longbench_write.jsonl
evalscope/third_party/longbench_write/resources/longbench_write_en.jsonl
evalscope/third_party/longbench_write/resources/longwrite_ruler.jsonl
evalscope/third_party/longbench_write/tools/__init__.py
evalscope/third_party/longbench_write/tools/data_etl.py
evalscope/third_party/longbench_write/tools/openai_api.py
evalscope/third_party/thinkbench/__init__.py
evalscope/third_party/thinkbench/eval.py
evalscope/third_party/thinkbench/infer.py
evalscope/third_party/thinkbench/resources/critique_template.txt
evalscope/third_party/thinkbench/resources/reformat_template.txt
evalscope/third_party/thinkbench/tools/__init__.py
evalscope/third_party/thinkbench/tools/llm.py
evalscope/third_party/thinkbench/tools/utils.py
evalscope/third_party/toolbench_static/README.md
evalscope/third_party/toolbench_static/__init__.py
evalscope/third_party/toolbench_static/config_default.json
evalscope/third_party/toolbench_static/config_default.yaml
evalscope/third_party/toolbench_static/eval.py
evalscope/third_party/toolbench_static/infer.py
evalscope/third_party/toolbench_static/requirements.txt
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/utils/__init__.py
evalscope/utils/arena_utils.py
evalscope/utils/chat_service.py
evalscope/utils/completion_parsers.py
evalscope/utils/deprecation_utils.py
evalscope/utils/filters.py
evalscope/utils/import_utils.py
evalscope/utils/io_utils.py
evalscope/utils/logger.py
evalscope/utils/model_utils.py
evalscope/utils/utils.py
requirements/aigc.txt
requirements/app.txt
requirements/docs.txt
requirements/framework.txt
requirements/opencompass.txt
requirements/perf.txt
requirements/rag.txt
requirements/vlmeval.txt
tests/__init__.py
tests/test_run_all.py
tests/aigc/__init__.py
tests/aigc/test_t2i.py
tests/cli/__init__.py
tests/cli/test_all.py
tests/cli/test_collection.py
tests/cli/test_run.py
tests/perf/__init__.py
tests/perf/test_perf.py
tests/rag/__init__.py
tests/rag/test_clip_benchmark.py
tests/rag/test_mteb.py
tests/rag/test_ragas.py
tests/swift/__init__.py
tests/swift/test_run_swift_eval.py
tests/swift/test_run_swift_vlm_eval.py
tests/swift/test_run_swift_vlm_jugde_eval.py
tests/vlm/__init__.py
tests/vlm/test_vlmeval.py