Run a rigorous A/B test on prompt variants for legal brief summarization, measuring user satisfaction (CSAT) on o1-mini using G-Eval.
Run a rigorous A/B test on prompt variants for legal brief summarization, measuring refusal rate on o3-mini using G-Eval.
Run a rigorous A/B test on prompt variants for legal brief summarization, measuring p95 latency on Command R+ using Trulens feedback functions.
Run a rigorous A/B test on prompt variants for legal brief summarization, measuring toolcall precision on Claude 3.5 Sonnet using DeepEval metrics.
Run a rigorous A/B test on prompt variants for legal brief summarization, measuring accuracy on Claude 4.5 Sonnet using promptfoo assertions.
Run a rigorous A/B test on prompt variants for legal brief summarization, measuring inter-judge agreement on Claude Haiku 4 using promptfoo assertions.
Run a rigorous A/B test on prompt variants for legal brief summarization, measuring toolcall precision on Gemini 2.0 Flash using embedding distance.
Run a rigorous A/B test on prompt variants for legal brief summarization, measuring cost-per-correct-answer on Llama 3.1 405B using tool-call accuracy.
Run a rigorous A/B test on prompt variants for legal brief summarization, measuring format-compliance rate on Mistral Small 3 using JSON schema validation.
Run a rigorous A/B test on prompt variants for legal brief summarization, measuring F1 score on o1-mini using JSON schema validation.
Run a rigorous A/B test on prompt variants for legal brief summarization, measuring cost-per-correct-answer on o3-mini using regex match checks.
Run a rigorous A/B test on prompt variants for legal brief summarization, measuring factuality on GPT-4.1 using BERTScore.