Benchmark Data Models (harness/models.py)

Defines structured data models for benchmarking AI agent performance and capabilities. Use this to standardize evaluation metrics and test results.

# Source: https://github.com/suyoumo/ClawProBench | License: Apache-2.0 | Copyright You must retain, in the Source form of any Derivative Works
# Provided via justclaw.it.com; keep this notice with the code.
"""Typed data models for OpenClawProBench."""

from __future__ import annotations

from dataclasses import dataclass, field
from enum import Enum
from pathlib import Path
from typing import Any


class Dimension(str, Enum):
    TOOL_USE = "tool_use"
    PLANNING = "planning"
    CONSTRAINTS = "constraints"
    ERROR_RECOVERY = "error_recovery"
    SYNTHESIS = "synthesis"
    SAFETY = "safety"


class Difficulty(str, Enum):
    EASY = "easy"
    MEDIUM = "medium"
    HARD = "hard"
    EXPERT = "expert"


class BenchmarkGroup(str, Enum):
    INTELLIGENCE = "intelligence"
    COVERAGE = "

... (truncated -- full source via MCP)