ChatGPT vs Claude: сравнение возможностей в 2025 году

# Пример: реализация LRU кэша

from collections import OrderedDict

class LRUCache:
    """LRU кэш с фиксированной емкостью"""
    def __init__(self, capacity: int):
        if capacity <= 0:
            raise ValueError("Capacity must be positive")
        self.cache = OrderedDict()
        self.capacity = capacity

    def get(self, key: int) -> int:
        if key not in self.cache:
            return -1
        self.cache.move_to_end(key)
        return self.cache[key]

    def put(self, key: int, value: int) -> None:
        if key in self.cache:
            self.cache.move_to_end(key)
        self.cache[key] = value
        if len(self.cache) > self.capacity:
            self.cache.popitem(last=False)

import anthropic

client = anthropic.Anthropic(api_key="your-key")

# Работа с большим документом
with open("large_doc.txt", "r", encoding="utf-8") as f:
    document = f.read()

message = client.messages.create(
    model="claude-3-5-sonnet-20241022",
    max_tokens=4096,
    messages=[{
        "role": "user",
        "content": f"Проанализируй документ: {document}"
    }]
)

# ChatGPT GPT-4 Turbo
input_tokens = 10000
output_tokens = 2000

cost_chatgpt = (input_tokens / 1000 * 0.01) + (output_tokens / 1000 * 0.03)
print(f"ChatGPT: ${cost_chatgpt}")  # $0.16

# Claude 3.5 Sonnet
cost_claude = (input_tokens / 1000 * 0.003) + (output_tokens / 1000 * 0.015)
print(f"Claude: ${cost_claude}")  # $0.06

# Claude дешевле в 2.5 раза!

benchmarks = {
    "MMLU": {"GPT-4": 86.4, "Claude": 88.7},
    "HumanEval": {"GPT-4": 67.0, "Claude": 73.0},
    "GSM8K": {"GPT-4": 92.0, "Claude": 95.0}
}