Token-cost and latency reduction playbook for a sales lead qualification prompt running on Mistral Large, judged by embedding distance.
Token-cost and latency reduction playbook for a sales lead qualification prompt running on Qwen 2.5 72B, judged by tool-call accuracy.
Token-cost and latency reduction playbook for a sales lead qualification prompt running on o1-mini, judged by tool-call accuracy.
Token-cost and latency reduction playbook for a sales lead qualification prompt running on o3-mini, judged by JSON schema validation.
Token-cost and latency reduction playbook for a sales lead qualification prompt running on Command R+, judged by JSON schema validation.
Token-cost and latency reduction playbook for a sales lead qualification prompt running on GPT-4.1, judged by regex match checks.
Token-cost and latency reduction playbook for a sales lead qualification prompt running on Claude 3.7 Sonnet, judged by regex match checks.
Token-cost and latency reduction playbook for a sales lead qualification prompt running on Claude 4.5 Sonnet, judged by BERTScore.
Token-cost and latency reduction playbook for a sales lead qualification prompt running on Claude Haiku 4, judged by factuality with retrieval.
Token-cost and latency reduction playbook for a sales lead qualification prompt running on Gemini 2.0 Flash, judged by factuality with retrieval.
Token-cost and latency reduction playbook for a sales lead qualification prompt running on DeepSeek-R1, judged by LLM-as-judge.
Token-cost and latency reduction playbook for a sales lead qualification prompt running on Mistral Large, judged by LLM-as-judge.