i use triton inference server with vllm backend - i tell the model to generate json output - any recommendation to extract the decision, reasoning, confidence from the text_output? can openai/harmony ...
A comprehensive benchmarking tool that tests how well different Language Models adhere to structured output formats across multiple providers (OpenAI, Anthropic, Google, Groq, OpenRouter). 1 One-shot ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results