Token-cost and latency reduction playbook for a academic grading prompt running on Grok 3, judged by DeepEval metrics.
Token-cost and latency reduction playbook for a academic grading prompt running on GPT-4o, judged by promptfoo assertions.
Token-cost and latency reduction playbook for a academic grading prompt running on Claude 3.5 Sonnet, judged by promptfoo assertions.
Token-cost and latency reduction playbook for a academic grading prompt running on Claude 4 Sonnet, judged by embedding distance.
Token-cost and latency reduction playbook for a academic grading prompt running on Claude Opus 4.5, judged by embedding distance.
Token-cost and latency reduction playbook for a academic grading prompt running on Gemini 2.5 Pro, judged by tool-call accuracy.
Token-cost and latency reduction playbook for a academic grading prompt running on DeepSeek-V3, judged by JSON schema validation.
Token-cost and latency reduction playbook for a academic grading prompt running on Llama 3.3 70B, judged by JSON schema validation.
Token-cost and latency reduction playbook for a academic grading prompt running on Mistral Small 3, judged by regex match checks.
Token-cost and latency reduction playbook for a academic grading prompt running on Grok 3, judged by factuality with retrieval.
Token-cost and latency reduction playbook for a academic grading prompt running on Claude 4 Sonnet, judged by LLM-as-judge.
Token-cost and latency reduction playbook for a academic grading prompt running on Llama 3.3 70B, judged by semantic similarity.