The environment evaluates language models on logical reasoning tasks
2.4K
The Logic (LGC) environment evaluates language models on logical reasoning tasks from the Intellect-3-RL dataset. Tasks cover various types of logic puzzles and reasoning challenges that test formal reasoning capabilities.
import affinetes as af
import asyncio
import os
async def main():
# Load environment from Docker Hub
env = af.load_env(
image="affinefoundation/lgc:pi",
env_vars={"CHUTES_API_KEY": os.getenv("CHUTES_API_KEY")}
)
# Evaluate on a logic task
result = await env.evaluate(
model="deepseek-ai/DeepSeek-V3",
base_url="https://llm.chutes.ai/v1",
task_id=42, # Optional: index into dataset
)
print(f"Score: {result['score']}")
print(f"Success: {result['success']}")
await env.cleanup()
asyncio.run(main())
import affinetes as af
import asyncio
import os
async def main():
# Build image from local environment directory
image_tag = af.build_image_from_env(
env_path="environments/primeintellect/lgc",
image_tag="lgc:pi"
)
# Load environment
env = af.load_env(
image=image_tag,
env_vars={"CHUTES_API_KEY": os.getenv("CHUTES_API_KEY")}
)
# Evaluate on a logic task
result = await env.evaluate(
model="deepseek-ai/DeepSeek-V3",
base_url="https://llm.chutes.ai/v1",
task_id=42
)
print(f"Score: {result['score']}")
await env.cleanup()
asyncio.run(main())
Content type
Image
Digest
sha256:ef3031597…
Size
117.9 MB
Last updated
7 months ago
docker pull affinefoundation/lgc:pi-v2