# decision model

OpenRouter compared three ways to get reliable JSON out of models, using 24 messy support messages across nine models that support structured outputs: send a strict JSON Schema, force a single tool call, or switch to a decision model that only returns labels. Across the nine models, 209 of 216 replies matched a strict schema, and all 7 misses came from one provider that ignores the schema; asking for JSON only in the prompt produced 18 failures, each from a code fence. For GLM 5.3 FlashX, which only supports tools, forcing the tool call gave 22 valid outputs out of 24, against 0 when the schema was sent directly.

OpenRouter compared three ways to get reliable JSON out of models, using 24 messy support messages across nine models that support structured outputs: send a strict JSON Schema, force a single tool call, or switch to a decision model that only returns labels. Across the nine models, 209 of 216 replies matched a strict schema, and all 7 misses came from one provider that ignores the schema; asking for JSON only in the prompt produced 18 failures, each from a code fence. For GLM 5.3 FlashX, which only supports tools, forcing the tool call gave 22 valid outputs out of 24, against 0 when the schema was sent directly.

Drex turns choosing into a single forward pass: given a context, a question and a set of options, the model returns a probability for every option instead of parsing text written by a large model. Drex Max, the largest of four open decision models, scores 67.52 on the public Decision Index 0.4.1 suite against 60.70 for Jev 1.14.0, and drops less than a point when private tests are added. On Decision Bench v4 with raw image input it is statistically tied with d3-turbo and GPT-6 Sol, answering a typical request in 183 ms.

Drex turns choosing into a single forward pass: given a context, a question and a set of options, the model returns a probability for every option instead of parsing text written by a large model. Drex Max, the largest of four open decision models, scores 67.52 on the public Decision Index 0.4.1 suite against 60.70 for Jev 1.14.0, and drops less than a point when private tests are added. On Decision Bench v4 with raw image input it is statistically tied with d3-turbo and GPT-6 Sol, answering a typical request in 183 ms.

Nace released Drex Max, a decision model that reads screenshots, screencasts, scanned documents, charts or photos and, given a set of typed questions, returns a probability for every supplied option in one forward pass. A computer-use agent can face about thirty such small decisions in a single task, and each one previously meant sending a screenshot to a large frontier model and waiting seconds; Drex Max scores 67.6 on the public Decision Index 0.4.0 against 61.3 for Drex v2.0, with a median API latency of 183 ms and $0.06 per 1,000 decisions.

Nace released Drex Max, a decision model that reads screenshots, screencasts, scanned documents, charts or photos and, given a set of typed questions, returns a probability for every supplied option in one forward pass. A computer-use agent can face about thirty such small decisions in a single task, and each one previously meant sending a screenshot to a large frontier model and waiting seconds; Drex Max scores 67.6 on the public Decision Index 0.4.0 against 61.3 for Drex v2.0, with a median API latency of 183 ms and $0.06 per 1,000 decisions.

Drex replaces asking a large model to generate text and parsing an answer with a single forward pass that scores each supplied option. The largest of the four open models, Drex Max, scores 67.52 on the public Decision Index 0.4.1 suite against 60.70 for Jev 1.14.0, and drops less than a point when private tests are added. On Decision Bench v4 it is statistically tied with d3-turbo and GPT-6 Sol and 1.6 points behind Claude Opus 5.5, while answering a typical request in 183 ms.

Drex replaces asking a large model to generate text and parsing an answer with a single forward pass that scores each supplied option. The largest of the four open models, Drex Max, scores 67.52 on the public Decision Index 0.4.1 suite against 60.70 for Jev 1.14.0, and drops less than a point when private tests are added. On Decision Bench v4 it is statistically tied with d3-turbo and GPT-6 Sol and 1.6 points behind Claude Opus 5.5, while answering a typical request in 183 ms.

Base Labs released joey-1, a 2B decision model that answers label-style calls such as routing a ticket or flagging a message by returning a single token and a calibrated probability in one forward pass, instead of generating text. At production scale it serves the average 2,000-token request at a P50 end-to-end latency of 20 ms, about 2.5x faster than elephant-1 at 49 ms, and at $0.01 per million tokens it costs a tenth of mammoth-1.

Base Labs released joey-1, a 2B decision model that answers label-style calls such as routing a ticket or flagging a message by returning a single token and a calibrated probability in one forward pass, instead of generating text. At production scale it serves the average 2,000-token request at a P50 end-to-end latency of 20 ms, about 2.5x faster than elephant-1 at 49 ms, and at $0.01 per million tokens it costs a tenth of mammoth-1.

Baseten's research lab released two open-source decision models, mammoth-1 (27B) and elephant-1 (9B), which return a probability distribution over every possible answer instead of generating text. mammoth-1 ranks first among 208 decision models on the Jev Decision Index 0.4, while elephant-1 is tied for eighth there and is the leading 9B decision model, and is tied for first with d1-ultra on the separate Artificial Analysis Decision Index. Both were post-trained from Qwen3.5-9B and Qwen3.5-27B on 6.21 million decision-making examples, are free to try for a week on Baseten Model APIs, and are open-source on Hugging Face.

Baseten's research lab released two open-source decision models, mammoth-1 (27B) and elephant-1 (9B), which return a probability distribution over every possible answer instead of generating text. mammoth-1 ranks first among 208 decision models on the Jev Decision Index 0.4, while elephant-1 is tied for eighth there and is the leading 9B decision model, and is tied for first with d1-ultra on the separate Artificial Analysis Decision Index. Both were post-trained from Qwen3.5-9B and Qwen3.5-27B on 6.21 million decision-making examples, are free to try for a week on Baseten Model APIs, and are open-source on Hugging Face.