Poetiq has developed a Meta-System that automatically creates an inference harness, significantly improving LLM performance on coding benchmarks without any model fine-tuning. This system achieved state-of-the-art results on LiveCodeBench Pro, boosting GPT 5.5 High's score from 89.6% to 93.9% and Gemini 3.1 Pro's from 78.6% to 90.9%. The Meta-System's harness is designed to be model-agnostic, demonstrating its ability to enhance various LLMs by optimizing prompting, output structuring, and evaluation processes. AI
IMPACT Demonstrates a novel method for enhancing LLM coding capabilities without fine-tuning, potentially improving efficiency and accessibility of AI tools.
RANK_REASON The cluster reports on a new system that achieved state-of-the-art results on a competitive coding benchmark, detailing its methodology and impact on LLM performance.
AI-generated summary · Google Gemini · from 4 sources. How we write summaries →
