Skip to main content

​
Basic Usage

import asyncio
from upsonic import Agent, Task
from upsonic.eval import PerformanceEvaluator

agent = Agent(
    model="anthropic/claude-sonnet-4-5",
    name="Assistant",
)

task = Task(description="What is 5 + 5?")

evaluator = PerformanceEvaluator(
    agent_under_test=agent,
    task=task,
    num_iterations=5,
    warmup_runs=2,
)

result = asyncio.run(evaluator.run(print_results=True))

print(f"Avg latency: {result.latency_stats['average'] * 1000:.0f} ms")
print(f"Median latency: {result.latency_stats['median'] * 1000:.0f} ms")
print(f"Min/Max: {result.latency_stats['min'] * 1000:.0f} ms / {result.latency_stats['max'] * 1000:.0f} ms")

​
With a Task List

When a list of tasks is provided, the Agent executes the first task in the list for each iteration. 
import asyncio
from upsonic import Agent, Task
from upsonic.eval import PerformanceEvaluator

agent = Agent(
    model="anthropic/claude-sonnet-4-5",
    name="Assistant",
)

tasks = [
    Task(description="What is 3 * 3?"),
    Task(description="What is 7 + 2?"),
]

evaluator = PerformanceEvaluator(
    agent_under_test=agent,
    task=tasks,
    num_iterations=3,
    warmup_runs=1,
)

result = asyncio.run(evaluator.run(print_results=True))

for run in result.all_runs:
    print(f"  Latency: {run.latency_seconds:.2f}s | Memory increase: {run.memory_increase_bytes} bytes")