§ feed · storyline
Poetiq's system boosts every LLM tested on LiveCodeBench Pro
Poetiq's Meta-System raises benchmark scores for every LLM tested on LiveCodeBench Pro without fine-tuning, lifting Gemini 3.1 Pro from 78.6% to 90.9% and GPT 5.5 High to 93.9%.
Poetiq's Meta-System automatically builds a model-agnostic harness that improved every LLM tested on LiveCodeBench Pro without fine-tuning, boosting Gemini 3.1 Pro from 78.6% to 90.9% and GPT 5.5 High to 93.9%.
§ sources1 publication · timeline below