Cutting LLM Costs Without Cutting Quality: How to Beat Proprietary LLMs with Fine-Tuned Open Source

Evaluating AI models using an LLM as a judge

Tomislav Tipurić +1 · World Congress 2026 North America

Key takeaways and open-source resources for model evaluation

Viktoria Semaan · World Congress 2026 North America

Evaluating model performance and accuracy using LLM judges

Viktoria Semaan · World Congress 2026 North America

Architecting inference layers and meta harnesses to manage token costs

Hari Lingamagunta +3 · World Congress 2026 North America

Comparing open-weight, proprietary, and fine-tuned AI models

Viktoria Semaan · World Congress 2026 North America

Navigating intelligence, speed, and cost trade-offs in AI models

Viktoria Semaan · World Congress 2026 North America