CITATION.cff
LICENSE
MANIFEST.in
README_PYPI.md
pyproject.toml
setup.py
configs/decoding.json
configs/environments.json
configs/models.json
configs/chat-templates/qwen3.5-large.jinja
configs/chat-templates/qwen3.5-small.jinja
configs/chat-templates/qwen3.jinja
configs/runs/balanced-qwen3-1.7b.json
configs/runs/balanced-qwen3-14b.json
configs/runs/initial-qwen3-1.7b.json
configs/runs/ladder-qwen3-14b.json
configs/runs/main-free-gpt-oss-120b-think.json
configs/runs/main-free-gpt-oss-20b-think.json
configs/runs/main-free-qwen3-0.6b-nothink.json
configs/runs/main-free-qwen3-0.6b-think.json
configs/runs/main-free-qwen3-1.7b-nothink.json
configs/runs/main-free-qwen3-1.7b-think.json
configs/runs/main-free-qwen3-14b-nothink.json
configs/runs/main-free-qwen3-14b-think.json
configs/runs/main-free-qwen3-32b-nothink-sm80.json
configs/runs/main-free-qwen3-32b-nothink.json
configs/runs/main-free-qwen3-32b-think-sm80.json
configs/runs/main-free-qwen3-32b-think.json
configs/runs/main-free-qwen3-4b-nothink.json
configs/runs/main-free-qwen3-4b-think.json
configs/runs/main-free-qwen3-8b-nothink.json
configs/runs/main-free-qwen3-8b-think.json
configs/runs/main-free-qwen3.5-0.8b-nothink.json
configs/runs/main-free-qwen3.5-0.8b-think.json
configs/runs/main-free-qwen3.5-122b-a10b-nothink.json
configs/runs/main-free-qwen3.5-122b-a10b-think.json
configs/runs/main-free-qwen3.5-27b-nothink.json
configs/runs/main-free-qwen3.5-27b-think.json
configs/runs/main-free-qwen3.5-2b-nothink.json
configs/runs/main-free-qwen3.5-2b-think.json
configs/runs/main-free-qwen3.5-35b-a3b-nothink.json
configs/runs/main-free-qwen3.5-35b-a3b-think.json
configs/runs/main-free-qwen3.5-4b-nothink.json
configs/runs/main-free-qwen3.5-4b-think.json
configs/runs/main-free-qwen3.5-9b-nothink.json
configs/runs/main-free-qwen3.5-9b-think.json
configs/runs/main-ladder-gpt-oss-120b-think.json
configs/runs/main-ladder-gpt-oss-20b-think.json
configs/runs/main-ladder-qwen3-0.6b-nothink.json
configs/runs/main-ladder-qwen3-0.6b-think.json
configs/runs/main-ladder-qwen3-1.7b-nothink.json
configs/runs/main-ladder-qwen3-1.7b-think.json
configs/runs/main-ladder-qwen3-14b-nothink.json
configs/runs/main-ladder-qwen3-14b-think.json
configs/runs/main-ladder-qwen3-32b-nothink-sm80.json
configs/runs/main-ladder-qwen3-32b-nothink.json
configs/runs/main-ladder-qwen3-32b-think-sm80.json
configs/runs/main-ladder-qwen3-32b-think.json
configs/runs/main-ladder-qwen3-4b-nothink.json
configs/runs/main-ladder-qwen3-4b-think.json
configs/runs/main-ladder-qwen3-8b-nothink.json
configs/runs/main-ladder-qwen3-8b-think.json
configs/runs/main-ladder-qwen3.5-0.8b-nothink.json
configs/runs/main-ladder-qwen3.5-0.8b-think.json
configs/runs/main-ladder-qwen3.5-122b-a10b-nothink.json
configs/runs/main-ladder-qwen3.5-122b-a10b-think.json
configs/runs/main-ladder-qwen3.5-27b-nothink.json
configs/runs/main-ladder-qwen3.5-27b-think.json
configs/runs/main-ladder-qwen3.5-2b-nothink.json
configs/runs/main-ladder-qwen3.5-2b-think.json
configs/runs/main-ladder-qwen3.5-35b-a3b-nothink.json
configs/runs/main-ladder-qwen3.5-35b-a3b-think.json
configs/runs/main-ladder-qwen3.5-4b-nothink.json
configs/runs/main-ladder-qwen3.5-4b-think.json
configs/runs/main-ladder-qwen3.5-9b-nothink.json
configs/runs/main-ladder-qwen3.5-9b-think.json
configs/runs/main-load-gpt-oss-120b-think.json
configs/runs/main-load-gpt-oss-20b-think.json
configs/runs/main-load-qwen3-0.6b-nothink.json
configs/runs/main-load-qwen3-0.6b-think.json
configs/runs/main-load-qwen3-1.7b-nothink.json
configs/runs/main-load-qwen3-1.7b-think.json
configs/runs/main-load-qwen3-14b-nothink.json
configs/runs/main-load-qwen3-14b-think.json
configs/runs/main-load-qwen3-32b-nothink-sm80.json
configs/runs/main-load-qwen3-32b-nothink.json
configs/runs/main-load-qwen3-32b-think-sm80.json
configs/runs/main-load-qwen3-32b-think.json
configs/runs/main-load-qwen3-4b-nothink.json
configs/runs/main-load-qwen3-4b-think.json
configs/runs/main-load-qwen3-8b-nothink.json
configs/runs/main-load-qwen3-8b-think.json
configs/runs/main-load-qwen3.5-0.8b-nothink.json
configs/runs/main-load-qwen3.5-0.8b-think.json
configs/runs/main-load-qwen3.5-122b-a10b-nothink.json
configs/runs/main-load-qwen3.5-122b-a10b-think.json
configs/runs/main-load-qwen3.5-27b-nothink.json
configs/runs/main-load-qwen3.5-27b-think.json
configs/runs/main-load-qwen3.5-2b-nothink.json
configs/runs/main-load-qwen3.5-2b-think.json
configs/runs/main-load-qwen3.5-35b-a3b-nothink.json
configs/runs/main-load-qwen3.5-35b-a3b-think.json
configs/runs/main-load-qwen3.5-4b-nothink.json
configs/runs/main-load-qwen3.5-4b-think.json
configs/runs/main-load-qwen3.5-9b-nothink.json
configs/runs/main-load-qwen3.5-9b-think.json
configs/runs/main-message-gpt-oss-120b-think.json
configs/runs/main-message-gpt-oss-20b-think.json
configs/runs/main-message-qwen3-0.6b-nothink.json
configs/runs/main-message-qwen3-0.6b-think.json
configs/runs/main-message-qwen3-1.7b-nothink.json
configs/runs/main-message-qwen3-1.7b-think.json
configs/runs/main-message-qwen3-14b-nothink.json
configs/runs/main-message-qwen3-14b-think.json
configs/runs/main-message-qwen3-32b-nothink-sm80.json
configs/runs/main-message-qwen3-32b-nothink.json
configs/runs/main-message-qwen3-32b-think-sm80.json
configs/runs/main-message-qwen3-32b-think.json
configs/runs/main-message-qwen3-4b-nothink.json
configs/runs/main-message-qwen3-4b-think.json
configs/runs/main-message-qwen3-8b-nothink.json
configs/runs/main-message-qwen3-8b-think.json
configs/runs/main-message-qwen3.5-0.8b-nothink.json
configs/runs/main-message-qwen3.5-0.8b-think.json
configs/runs/main-message-qwen3.5-122b-a10b-nothink.json
configs/runs/main-message-qwen3.5-122b-a10b-think.json
configs/runs/main-message-qwen3.5-27b-nothink.json
configs/runs/main-message-qwen3.5-27b-think.json
configs/runs/main-message-qwen3.5-2b-nothink.json
configs/runs/main-message-qwen3.5-2b-think.json
configs/runs/main-message-qwen3.5-35b-a3b-nothink.json
configs/runs/main-message-qwen3.5-35b-a3b-think.json
configs/runs/main-message-qwen3.5-4b-nothink.json
configs/runs/main-message-qwen3.5-4b-think.json
configs/runs/main-message-qwen3.5-9b-nothink.json
configs/runs/main-message-qwen3.5-9b-think.json
configs/runs/main-operator-gpt-oss-120b-think.json
configs/runs/main-operator-gpt-oss-20b-think.json
configs/runs/main-operator-qwen3-0.6b-nothink.json
configs/runs/main-operator-qwen3-0.6b-think.json
configs/runs/main-operator-qwen3-1.7b-nothink.json
configs/runs/main-operator-qwen3-1.7b-think.json
configs/runs/main-operator-qwen3-14b-nothink.json
configs/runs/main-operator-qwen3-14b-think.json
configs/runs/main-operator-qwen3-32b-nothink-sm80.json
configs/runs/main-operator-qwen3-32b-nothink.json
configs/runs/main-operator-qwen3-32b-think-sm80.json
configs/runs/main-operator-qwen3-32b-think.json
configs/runs/main-operator-qwen3-4b-nothink.json
configs/runs/main-operator-qwen3-4b-think.json
configs/runs/main-operator-qwen3-8b-nothink.json
configs/runs/main-operator-qwen3-8b-think.json
configs/runs/main-operator-qwen3.5-0.8b-nothink.json
configs/runs/main-operator-qwen3.5-0.8b-think.json
configs/runs/main-operator-qwen3.5-122b-a10b-nothink.json
configs/runs/main-operator-qwen3.5-122b-a10b-think.json
configs/runs/main-operator-qwen3.5-27b-nothink.json
configs/runs/main-operator-qwen3.5-27b-think.json
configs/runs/main-operator-qwen3.5-2b-nothink.json
configs/runs/main-operator-qwen3.5-2b-think.json
configs/runs/main-operator-qwen3.5-35b-a3b-nothink.json
configs/runs/main-operator-qwen3.5-35b-a3b-think.json
configs/runs/main-operator-qwen3.5-4b-nothink.json
configs/runs/main-operator-qwen3.5-4b-think.json
configs/runs/main-operator-qwen3.5-9b-nothink.json
configs/runs/main-operator-qwen3.5-9b-think.json
configs/runs/main-realism-gpt-oss-120b-think.json
configs/runs/main-realism-gpt-oss-20b-think.json
configs/runs/main-realism-qwen3-0.6b-nothink.json
configs/runs/main-realism-qwen3-0.6b-think.json
configs/runs/main-realism-qwen3-1.7b-nothink.json
configs/runs/main-realism-qwen3-1.7b-think.json
configs/runs/main-realism-qwen3-14b-nothink.json
configs/runs/main-realism-qwen3-14b-think.json
configs/runs/main-realism-qwen3-32b-nothink-sm80.json
configs/runs/main-realism-qwen3-32b-nothink.json
configs/runs/main-realism-qwen3-32b-think-sm80.json
configs/runs/main-realism-qwen3-32b-think.json
configs/runs/main-realism-qwen3-4b-nothink.json
configs/runs/main-realism-qwen3-4b-think.json
configs/runs/main-realism-qwen3-8b-nothink.json
configs/runs/main-realism-qwen3-8b-think.json
configs/runs/main-realism-qwen3.5-0.8b-nothink.json
configs/runs/main-realism-qwen3.5-0.8b-think.json
configs/runs/main-realism-qwen3.5-122b-a10b-nothink.json
configs/runs/main-realism-qwen3.5-122b-a10b-think.json
configs/runs/main-realism-qwen3.5-27b-nothink.json
configs/runs/main-realism-qwen3.5-27b-think.json
configs/runs/main-realism-qwen3.5-2b-nothink.json
configs/runs/main-realism-qwen3.5-2b-think.json
configs/runs/main-realism-qwen3.5-35b-a3b-nothink.json
configs/runs/main-realism-qwen3.5-35b-a3b-think.json
configs/runs/main-realism-qwen3.5-4b-nothink.json
configs/runs/main-realism-qwen3.5-4b-think.json
configs/runs/main-realism-qwen3.5-9b-nothink.json
configs/runs/main-realism-qwen3.5-9b-think.json
configs/runs/main-tier-gpt-oss-120b-think.json
configs/runs/main-tier-gpt-oss-20b-think.json
configs/runs/main-tier-qwen3-0.6b-nothink.json
configs/runs/main-tier-qwen3-0.6b-think.json
configs/runs/main-tier-qwen3-1.7b-nothink.json
configs/runs/main-tier-qwen3-1.7b-think.json
configs/runs/main-tier-qwen3-14b-nothink.json
configs/runs/main-tier-qwen3-14b-think.json
configs/runs/main-tier-qwen3-32b-nothink-sm80.json
configs/runs/main-tier-qwen3-32b-nothink.json
configs/runs/main-tier-qwen3-32b-think-sm80.json
configs/runs/main-tier-qwen3-32b-think.json
configs/runs/main-tier-qwen3-4b-nothink.json
configs/runs/main-tier-qwen3-4b-think.json
configs/runs/main-tier-qwen3-8b-nothink.json
configs/runs/main-tier-qwen3-8b-think.json
configs/runs/main-tier-qwen3.5-0.8b-nothink.json
configs/runs/main-tier-qwen3.5-0.8b-think.json
configs/runs/main-tier-qwen3.5-122b-a10b-nothink.json
configs/runs/main-tier-qwen3.5-122b-a10b-think.json
configs/runs/main-tier-qwen3.5-27b-nothink.json
configs/runs/main-tier-qwen3.5-27b-think.json
configs/runs/main-tier-qwen3.5-2b-nothink.json
configs/runs/main-tier-qwen3.5-2b-think.json
configs/runs/main-tier-qwen3.5-35b-a3b-nothink.json
configs/runs/main-tier-qwen3.5-35b-a3b-think.json
configs/runs/main-tier-qwen3.5-4b-nothink.json
configs/runs/main-tier-qwen3.5-4b-think.json
configs/runs/main-tier-qwen3.5-9b-nothink.json
configs/runs/main-tier-qwen3.5-9b-think.json
configs/vllm/gpt-oss-120b.yaml
configs/vllm/gpt-oss-20b.yaml
configs/vllm/qwen3-0.6b.yaml
configs/vllm/qwen3-1.7b.yaml
configs/vllm/qwen3-14b.yaml
configs/vllm/qwen3-32b-sm80.yaml
configs/vllm/qwen3-32b.yaml
configs/vllm/qwen3-4b.yaml
configs/vllm/qwen3-8b.yaml
configs/vllm/qwen3.5-0.8b.yaml
configs/vllm/qwen3.5-122b-a10b.yaml
configs/vllm/qwen3.5-27b.yaml
configs/vllm/qwen3.5-2b.yaml
configs/vllm/qwen3.5-35b-a3b.yaml
configs/vllm/qwen3.5-4b.yaml
configs/vllm/qwen3.5-9b.yaml
data/load/lb-02.json
data/load/lb-03.json
data/load/lb-04.json
data/load/lb-05.json
data/load/lb-06.json
data/load/lb-07.json
data/load/lb-08.json
data/load/lb-09.json
data/load/lb-10.json
data/realism/batches.json
data/realism/rs-01.json
data/realism/rs-02.json
data/realism/rs-03.json
data/realism/rs-04.json
data/realism/rs-05.json
data/scenarios/format/fmt-0001-0010.json
data/scenarios/format/fmt-0011-0060.json
data/scenarios/format/fmt-0061-0110.json
data/scenarios/format/fmt-0111-0160.json
data/scenarios/format/fmt-0161-0210.json
data/scenarios/format/fmt-0211-0240.json
data/scenarios/ordering/ord-0001-0010.json
data/scenarios/ordering/ord-0011-0060.json
data/scenarios/ordering/ord-0061-0110.json
data/scenarios/ordering/ord-0111-0160.json
data/scenarios/ordering/ord-0161-0210.json
data/scenarios/ordering/ord-0211-0240.json
data/scenarios/path/path-0001-0010.json
data/scenarios/path/path-0011-0060.json
data/scenarios/path/path-0061-0110.json
data/scenarios/path/path-0111-0160.json
data/scenarios/path/path-0161-0210.json
data/scenarios/path/path-0211-0240.json
data/scenarios/refusal/ref-0001-0010.json
data/scenarios/refusal/ref-0011-0060.json
data/scenarios/refusal/ref-0061-0110.json
data/scenarios/refusal/ref-0111-0120.json
data/scenarios/tool/tool-0001-0010.json
data/scenarios/tool/tool-0011-0060.json
data/scenarios/tool/tool-0061-0110.json
data/scenarios/tool/tool-0111-0160.json
data/scenarios/tool/tool-0161-0210.json
data/scenarios/tool/tool-0211-0240.json
data/splits/axis.json
data/splits/domain.json
data/splits/item.json
data/splits/set.json
data/splits/source_pair.json
data/trials/01-decomposition.json
data/trials/02-composition.json
data/trials/03-load.json
data/trials/04-declared-tier.json
data/trials/05-binding.json
data/trials/06-authorship.json
data/trials/07-harness.json
src/whowins/__init__.py
src/whowins/data.py
src/whowins/logs.py
src/whowins/progress.py
src/whowins.egg-info/PKG-INFO
src/whowins.egg-info/SOURCES.txt
src/whowins.egg-info/dependency_links.txt
src/whowins.egg-info/requires.txt
src/whowins.egg-info/top_level.txt
src/whowins/checkers/__init__.py
src/whowins/checkers/core.py
src/whowins/checkers/coverage.py
src/whowins/checkers/trace.py
src/whowins/checkers/fmt/__init__.py
src/whowins/checkers/fmt/_lib.py
src/whowins/checkers/fmt/domain.py
src/whowins/checkers/fmt/editorial.py
src/whowins/checkers/fmt/prose.py
src/whowins/checkers/fmt/structural.py
src/whowins/checkers/fmt/surface.py
src/whowins/checkers/fmt/syntax.py
src/whowins/checkers/fmt/tooling.py
src/whowins/checkers/fmt/values.py
src/whowins/checkers/fmt/wire.py
src/whowins/runner/__init__.py
src/whowins/runner/analyse.py
src/whowins/runner/batch.py
src/whowins/runner/bundles.py
src/whowins/runner/compare.py
src/whowins/runner/design.py
src/whowins/runner/fillers.py
src/whowins/runner/layouts.py
src/whowins/runner/preflight.py
src/whowins/runner/rendering.py
src/whowins/runner/rescore.py
src/whowins/runner/response.py
src/whowins/runner/run.py
src/whowins/runner/serving.py
src/whowins/runner/spec.py
src/whowins/runner/tools.py
src/whowins/runner/trials.py
src/whowins/runner/vocabulary.py
src/whowins/splits/__init__.py
src/whowins/splits/axes.py
src/whowins/splits/build.py
src/whowins/splits/check.py
src/whowins/splits/grouping.py
src/whowins/splits/sources.py
src/whowins/stats/__init__.py
src/whowins/stats/capacity.py
src/whowins/stats/choice.py
src/whowins/stats/families.py
src/whowins/stats/ladder.py
src/whowins/stats/layouts.py
src/whowins/stats/load_cell.py
src/whowins/stats/mixed.py
src/whowins/stats/models.py
src/whowins/stats/normal.py
src/whowins/stats/paired.py
src/whowins/stats/phase1.py
src/whowins/stats/pooled.py
src/whowins/stats/power.py
src/whowins/stats/rankings.py
src/whowins/stats/regularity.py
src/whowins/stats/score.py
src/whowins/stats/simulate.py
src/whowins/stats/strengths.py
src/whowins/validation/__init__.py
src/whowins/validation/build_registry.py
src/whowins/validation/check_batch.py
src/whowins/validation/check_load.py
src/whowins/validation/check_realism.py
src/whowins/validation/validate_collection.py