To validate the choices and configurations, feel free to give it a reading. We also breakdown our methodology in the blog and in-depth within the paper.
General hallucinations benchmarks tend to be knowledge specific like GPQA or MMLU but none specifically measure structured output end-to-end which is one of the biggest use case for LLMs.
Many developer workflows use LLMs to produce structured artifacts due to it's flexibility of consuming unstructured inputs.
> "don't use an LLM"
Partially agree, that's what we're building towards at interfaze.ai a hybrid between transformers (LLMs) and traditional CNN/DNN architecture to solve this problem of "deterministic" output. This give devs the flexibility of custom schema definitions and unstructured input while still getting high quality structured output like you would get from a CNN models like EasyOCR.
The industry is moving toward using LLMs for more and more deterministic tasks so this benchmarks allows us to now measure it.
We ran the comparison and saw no difference, so to keep the bench consistent since some models don't support structured decoding we used greedy decoding on all models.
Yeah we selected models that are most commonly integrated in developer workflows and being used for structured output. Typically those models tend to be in the low -mid cost range and with no or low reasoning.
For the benchmark, was kept consistent across all models and typically opus and 3.1 pro would be overkill and expensive even with reasoning off.
Good point tho, will add this point in the blog too :)
Also the benchmark is open source, so anyone can run a model on it and create a PR too, the leaderboard is dynamic and will automatically add that in.
We define determinism as a model behaving predictably, while also producing useful supporting metadata, like confidence scores from specialized DNNs/CNNs, not just text tokens generated as "scores".
So for the same kind of task, you can expect the same kind of output every time, without randomly breaking structured output or having to constantly change generation hyperparams.
To validate the choices and configurations, feel free to give it a reading. We also breakdown our methodology in the blog and in-depth within the paper.