@ArizePhoenix: Decision models as evaluators Phoenix evals (TS) can now run any classification evaluator on a decision model, like gpt…
Summary
Arize Phoenix evals (TS) now supports running any classification evaluator on a decision model (e.g. gpt-6-luna via OpenAI's Decisions API), returning labels and probabilities per option with each call traced as a decision span.
View Cached Full Text
Cached at: 10/21/26, 06:34 PM
Decision models as evaluators
Phoenix evals (TS) can now run any classification evaluator on a decision model, like gpt-6-luna via OpenAI’s Decisions API. The evaluator returns a label and a probability per option, no text generated. Each call is traced as a decision span. https://t.co/itIJR6Iexz
Similar Articles
@ArizePhoenix: Who judges the evaluators? When you use LLM-as-a-judge, you’re trusting a model to decide whether your agent, workflow,…
The article discusses the challenges of debugging and evaluating LLM judges using Arize Phoenix, which traces evaluator runs via OpenTelemetry to inspect decision logic, costs, and potential biases.
@OpenAIDevs: Give your app real-time decision-making with Decisions API, powered by GPT-6 Luna. Define questions and possible answer…
OpenAI announced the Decisions API in limited preview, powered by GPT-6 Luna, enabling apps to define questions and answer options for real-time content classification, request routing, and agent action selection.
@ArizePhoenix: Experiment Baselining and Charts When trying to determine if a new model is up to the task, you need to factor in many …
Phoenix now includes customizable experiment charts and baselining, allowing users to compare models along performance, latency, tokens, and cost dimensions, and set baselines for preferred models.
@george_onx: Decision models should do more than pick a label. To truly act, they need to extract evidence, understand relationships…
GLiNER2.5-Decide is a specialist decision model that extracts evidence, understands relationships, and produces structured records for operational tasks, featuring fast inference and fine-tuning capabilities via a new API.
@sgl_project: We turned Qwen3.8-27B into a multimodal decision model. It beat Pokémon FireRed’s elite four and champion with sub-100 …
SGLang project turned Qwen3.8-27B into a multimodal decision model that beat Pokémon FireRed's elite four and champion with sub-100 ms decisions from live game state, and shipped native /v1/decisions plus /v1/systemone endpoints for classifying, scoring, and integrating open models with the TypeSafe SDK.