LICENSE
README.md
pyproject.toml
src/omniedu/__init__.py
src/omniedu/api.py
src/omniedu/cli.py
src/omniedu/io.py
src/omniedu/media.py
src/omniedu/presets.py
src/omniedu/tasks.json
src/omniedu/tasks.py
src/omniedu/types.py
src/omniedu.egg-info/PKG-INFO
src/omniedu.egg-info/SOURCES.txt
src/omniedu.egg-info/dependency_links.txt
src/omniedu.egg-info/entry_points.txt
src/omniedu.egg-info/requires.txt
src/omniedu.egg-info/top_level.txt
src/omniedu/backends/__init__.py
src/omniedu/backends/base.py
src/omniedu/backends/openai_backend.py
src/omniedu/backends/transformers_backend.py
src/omniedu/eval/__init__.py
src/omniedu/eval/benchmarks.json
src/omniedu/eval/bundle.py
src/omniedu/eval/cli.py
src/omniedu/eval/client.py
src/omniedu/eval/engine.py
src/omniedu/eval/io.py
src/omniedu/eval/media.py
src/omniedu/eval/metrics.py
src/omniedu/eval/registry.py
src/omniedu/eval/report.py
src/omniedu/eval/resources.py
src/omniedu/eval/sampling.py
src/omniedu/eval/benchmarks/__init__.py
src/omniedu/eval/benchmarks/edumath.py
src/omniedu/eval/benchmarks/exams_v.py
src/omniedu/eval/benchmarks/gaokao.py
src/omniedu/eval/benchmarks/gpqa.py
src/omniedu/eval/benchmarks/ifeval.py
src/omniedu/eval/benchmarks/k12bench.py
src/omniedu/eval/benchmarks/longtutor.py
src/omniedu/eval/benchmarks/mathfish.py
src/omniedu/eval/benchmarks/mathtutorbench.py
src/omniedu/eval/benchmarks/mdk12.py
src/omniedu/eval/benchmarks/mmmu_pro.py
src/omniedu/eval/benchmarks/tutorbench.py
src/omniedu/eval/clean/exams_v/image_decontamination_report.json
src/omniedu/eval/clean/exams_v/keep_ids.json
src/omniedu/eval/clean/mdk12_bench/keep_ids.json
src/omniedu/eval/clean/tutorbench/keep_ids.json
src/omniedu/eval/judge/__init__.py
src/omniedu/eval/judge/cli.py
src/omniedu/eval/judge/judge_gaokao_edumath.py
src/omniedu/eval/judge/judge_longtutor.py
src/omniedu/eval/judge/judge_mdk12_tutorbench.py
src/omniedu/eval/judge/reward_mathtutorbench.py
src/omniedu/eval/judge/prompts/edumath_official.txt
src/omniedu/eval/judge/prompts/edumath_query.txt
src/omniedu/eval/judge/prompts/gaokao_query.txt
src/omniedu/eval/judge/prompts/gaokao_subject_prompts.json
src/omniedu/eval/mathtutorbench/clean_datasets/mathdial_bridge_clean.json
src/omniedu/eval/mathtutorbench/clean_datasets/mathdial_bridge_hard_clean.json
src/omniedu/eval/mathtutorbench/configs/pedagogy_following.yaml
src/omniedu/eval/mathtutorbench/configs/pedagogy_following_hard.yaml
src/omniedu/eval/mathtutorbench/configs/scaffolding_generation.yaml
src/omniedu/eval/mathtutorbench/configs/scaffolding_generation_hard.yaml
src/omniedu/eval/vendor/ifeval_official/instructions.py
src/omniedu/eval/vendor/ifeval_official/instructions_registry.py
src/omniedu/eval/vendor/ifeval_official/instructions_util.py
tests/test_api.py
tests/test_cli.py
tests/test_eval_cli.py
tests/test_eval_metrics.py
tests/test_io.py
tests/test_media.py
tests/test_openai_backend.py
tests/test_presets.py
tests/test_readme_commands.py
tests/test_tasks.py