Poetiq meta-system builds model-agnostic harness; boosts every LLM tested
Poetiq constructed a code-execution harness for LiveCodeBench Pro using only Gemini 3.1 Pro, no fine-tuning or model internals access.
The same harness, applied unmodified to GPT 5.5 High, Kimi K2.6, Gemini 3.0 Flash, and four other models, improved performance across all of them.