Swarms vs LangGraph vs CrewAI vs AutoGen: Benchmark on a Real Research Task

import os
import requests
from dotenv import load_dotenv

load_dotenv()

API_KEY = os.environ["SWARMS_API_KEY"]
BASE_URL = "https://api.swarms.world"
headers = {"x-api-key": API_KEY, "Content-Type": "application/json"}

PM_PROMPT = (
    "You are a Portfolio Manager. Read the Fundamentals, Technicals, and Macro briefs. "
    "Produce a one-page memo ending with: CALL (BUY|SELL|HOLD), CONVICTION (LOW|MEDIUM|HIGH), "
    "KEY SIGNAL (one sentence), RISK (one sentence). Be decisive."
)
FUND_PROMPT = "Fundamental analyst. NVDA only. Revenue, margins, FCF, balance sheet, top catalyst next 2Q. <200 words."
TECH_PROMPT = "Technical analyst. NVDA only. Trend, S/R, RSI, MACD, volume, near-term target + stop. <200 words."
MACRO_PROMPT = "Macro analyst. NVDA only. Rate regime, FX/commodity sensitivity, policy, risk-off behaviour. <200 words."

payload = {
    "name": "NVDA Investment Memo",
    "swarm_type": "HierarchicalSwarm",
    "max_loops": 1,
    "task": "Produce an investment memo on NVDA. Each analyst writes their brief, then the PM issues a final call.",
    "agents": [
        {"agent_name": "Portfolio Manager", "system_prompt": PM_PROMPT,    "model_name": "gpt-4.1", "role": "coordinator", "max_tokens": 4096, "temperature": 0.2},
        {"agent_name": "Fundamentals",      "system_prompt": FUND_PROMPT,  "model_name": "gpt-4.1", "role": "worker",      "max_tokens": 1024, "temperature": 0.4},
        {"agent_name": "Technicals",        "system_prompt": TECH_PROMPT,  "model_name": "gpt-4.1", "role": "worker",      "max_tokens": 1024, "temperature": 0.4},
        {"agent_name": "Macro",             "system_prompt": MACRO_PROMPT, "model_name": "gpt-4.1", "role": "worker",      "max_tokens": 1024, "temperature": 0.4},
    ],
}

r = requests.post(f"{BASE_URL}/v1/swarm/completions", headers=headers, json=payload, timeout=300)
print(r.json()["output"][-1]["content"])

import os
import operator
from typing import TypedDict, Annotated
from langgraph.graph import StateGraph, END
from langchain_openai import ChatOpenAI
from langchain_core.messages import SystemMessage, HumanMessage

llm = ChatOpenAI(model="gpt-4.1", temperature=0.4)
pm_llm = ChatOpenAI(model="gpt-4.1", temperature=0.2)

FUND_PROMPT  = "Fundamental analyst. NVDA only. Revenue, margins, FCF, balance sheet, top catalyst next 2Q. <200 words."
TECH_PROMPT  = "Technical analyst. NVDA only. Trend, S/R, RSI, MACD, volume, near-term target + stop. <200 words."
MACRO_PROMPT = "Macro analyst. NVDA only. Rate regime, FX/commodity sensitivity, policy, risk-off behaviour. <200 words."
PM_PROMPT    = (
    "You are a Portfolio Manager. Read the Fundamentals, Technicals, and Macro briefs. "
    "Produce a one-page memo ending with CALL/CONVICTION/KEY SIGNAL/RISK. Be decisive."
)

class State(TypedDict):
    ticker: str
    fundamentals: str
    technicals: str
    macro: str
    memo: str
    log: Annotated[list, operator.add]

def fundamentals_node(state: State) -> State:
    res = llm.invoke([
        SystemMessage(content=FUND_PROMPT),
        HumanMessage(content=f"Ticker: {state['ticker']}"),
    ])
    return {"fundamentals": res.content, "log": [("fundamentals", len(res.content))]}

def technicals_node(state: State) -> State:
    res = llm.invoke([
        SystemMessage(content=TECH_PROMPT),
        HumanMessage(content=f"Ticker: {state['ticker']}"),
    ])
    return {"technicals": res.content, "log": [("technicals", len(res.content))]}

def macro_node(state: State) -> State:
    res = llm.invoke([
        SystemMessage(content=MACRO_PROMPT),
        HumanMessage(content=f"Ticker: {state['ticker']}"),
    ])
    return {"macro": res.content, "log": [("macro", len(res.content))]}

def pm_node(state: State) -> State:
    briefing = (
        f"Ticker: {state['ticker']}\n\n"
        f"=== FUNDAMENTALS ===\n{state['fundamentals']}\n\n"
        f"=== TECHNICALS ===\n{state['technicals']}\n\n"
        f"=== MACRO ===\n{state['macro']}\n"
    )
    res = pm_llm.invoke([
        SystemMessage(content=PM_PROMPT),
        HumanMessage(content=briefing),
    ])
    return {"memo": res.content, "log": [("pm", len(res.content))]}

# A no-op router node we use as the parallel fan-out point.
def start_node(state: State) -> State:
    return {"log": [("start", 0)]}

graph = StateGraph(State)
graph.add_node("start",        start_node)
graph.add_node("fundamentals", fundamentals_node)
graph.add_node("technicals",   technicals_node)
graph.add_node("macro",        macro_node)
graph.add_node("pm",           pm_node)

graph.set_entry_point("start")
graph.add_edge("start", "fundamentals")
graph.add_edge("start", "technicals")
graph.add_edge("start", "macro")
graph.add_edge("fundamentals", "pm")
graph.add_edge("technicals",   "pm")
graph.add_edge("macro",        "pm")
graph.add_edge("pm", END)

app = graph.compile()

result = app.invoke({
    "ticker": "NVDA",
    "fundamentals": "",
    "technicals": "",
    "macro": "",
    "memo": "",
    "log": [],
})
print(result["memo"])

import os
from crewai import Agent, Task, Crew, Process
from langchain_openai import ChatOpenAI

llm    = ChatOpenAI(model="gpt-4.1", temperature=0.4)
pm_llm = ChatOpenAI(model="gpt-4.1", temperature=0.2)

fundamentals_agent = Agent(
    role="Fundamental Equity Analyst",
    goal="Cover NVDA fundamentals: revenue, margins, FCF, balance sheet, top catalyst next 2Q.",
    backstory="Senior buy-side analyst. Concise. <200 words.",
    llm=llm, allow_delegation=False, verbose=False,
)

technicals_agent = Agent(
    role="Technical Analyst",
    goal="Cover NVDA technicals: trend, S/R, RSI, MACD, volume, target + stop.",
    backstory="Desk technician. Specific levels. <200 words.",
    llm=llm, allow_delegation=False, verbose=False,
)

macro_agent = Agent(
    role="Macro Analyst",
    goal="Cover NVDA macro: rates, FX, commodities, policy, risk-off behaviour.",
    backstory="Cross-asset macro. Concrete linkages only. <200 words.",
    llm=llm, allow_delegation=False, verbose=False,
)

pm_agent = Agent(
    role="Portfolio Manager",
    goal="Produce a decisive one-page NVDA memo ending with CALL/CONVICTION/KEY SIGNAL/RISK.",
    backstory="Long/short PM. Picks a side. Never hedges across all three lenses.",
    llm=pm_llm, allow_delegation=False, verbose=False,
)

fund_task = Task(
    description="Write the fundamentals brief on NVDA per the role goal.",
    expected_output="Under-200-word fundamentals brief.",
    agent=fundamentals_agent,
)

tech_task = Task(
    description="Write the technicals brief on NVDA per the role goal.",
    expected_output="Under-200-word technicals brief.",
    agent=technicals_agent,
)

macro_task = Task(
    description="Write the macro brief on NVDA per the role goal.",
    expected_output="Under-200-word macro brief.",
    agent=macro_agent,
)

pm_task = Task(
    description=(
        "Read the three analyst briefs in your context. Produce the final NVDA memo "
        "ending with CALL (BUY|SELL|HOLD), CONVICTION (LOW|MEDIUM|HIGH), "
        "KEY SIGNAL (one sentence), RISK (one sentence)."
    ),
    expected_output="A one-page investment memo with a decisive final call block.",
    agent=pm_agent,
    context=[fund_task, tech_task, macro_task],
)

crew = Crew(
    agents=[fundamentals_agent, technicals_agent, macro_agent, pm_agent],
    tasks=[fund_task, tech_task, macro_task, pm_task],
    process=Process.sequential,
    verbose=False,
)

result = crew.kickoff(inputs={"ticker": "NVDA"})
print(result)

import os
from autogen_agentchat.agents import AssistantAgent
from autogen_agentchat.teams import RoundRobinGroupChat
from autogen_agentchat.conditions import TextMentionTermination, MaxMessageTermination
from autogen_ext.models.openai import OpenAIChatCompletionClient

client    = OpenAIChatCompletionClient(model="gpt-4.1", temperature=0.4)
pm_client = OpenAIChatCompletionClient(model="gpt-4.1", temperature=0.2)

fundamentals = AssistantAgent(
    name="Fundamentals",
    model_client=client,
    system_message=(
        "You are the Fundamental Analyst on a NVDA memo team. Write a <200 word brief: "
        "revenue, margins, FCF, balance sheet, top catalyst next 2Q. "
        "End your turn with the literal token 'HANDOFF'."
    ),
)

technicals = AssistantAgent(
    name="Technicals",
    model_client=client,
    system_message=(
        "You are the Technical Analyst. Write a <200 word brief: trend, S/R, RSI, MACD, "
        "volume, near-term target + stop. End your turn with 'HANDOFF'."
    ),
)

macro = AssistantAgent(
    name="Macro",
    model_client=client,
    system_message=(
        "You are the Macro Analyst. Write a <200 word brief: rate regime, FX/commodities, "
        "policy, risk-off behaviour. End your turn with 'HANDOFF'."
    ),
)

pm = AssistantAgent(
    name="PortfolioManager",
    model_client=pm_client,
    system_message=(
        "You are the Portfolio Manager. Read the three analyst briefs in the chat history. "
        "Produce a one-page memo ending with CALL (BUY|SELL|HOLD), CONVICTION (LOW|MEDIUM|HIGH), "
        "KEY SIGNAL (one sentence), RISK (one sentence). Be decisive. "
        "End your message with the literal token 'TERMINATE'."
    ),
)

termination = TextMentionTermination("TERMINATE") | MaxMessageTermination(8)

team = RoundRobinGroupChat(
    participants=[fundamentals, technicals, macro, pm],
    termination_condition=termination,
)

result = await team.run(task="Produce an investment memo on NVDA. Each analyst goes once, then the PM issues the final call.")
print(result.messages[-1].content)