Skip to content

~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted.

478 B
Raw Blame
"""
Benchmark evaluation package.

This package provides evaluators for different benchmark types and
a composite evaluator for weighted multi-benchmark evaluation.
"""

from .base import BaseBenchmarkEvaluator
from .browsecomp import BrowseCompEvaluator
from .composite import CompositeBenchmarkEvaluator
from .simpleqa import SimpleQAEvaluator

__all__ = [
    "BaseBenchmarkEvaluator",
    "BrowseCompEvaluator",
    "CompositeBenchmarkEvaluator",
    "SimpleQAEvaluator",
]