Jev vs decider-4b

The analysis

Where Jev and decider-4b really differ, and why the bars above land where they do.

decider-4b v2 was the first system to finish above Jev on JevBench: it took first place when it was added in v1.4.2, and the benchmark’s independent check before listing it first found the result legitimate. On the re-measured v1.6 pool it is #39 of 135 at 41.2, with Jev #5 at 71.5. Where it still holds up is the two cheap axes: speed 91.8 against Jev’s 91.5, from a raw median of 25ms per decision, and the benchmark’s cost estimate for a 4B model, 64.5 against 54.7.

On the answers Jev is well ahead. Intelligence is 63.6 against 40.1. On the sealed half, the decisions nobody could tune for, Jev scores 61.6 against 35.0, and decider-4b’s gap between its open and sealed results, 10.2 points, is about four times the field median. Because its intelligence now sits below the benchmark’s floor of 50, the harmonic mean is scaled down, which is why its score falls to 41.2 while its individual axes look respectable.

So the official score and the Capability ranking disagree, and both are honest: decider-4b is #39 on the score but twenty-eighth on Capability, where speed and cost are left out. If your decisions are high-volume and mostly routine choices, and you can run a GPU, decider-4b is a fast, cheap option on choice questions, 65.0 against 77.4. If the cases that matter are hard or yes/no, Jev is the far more accurate model.

What decider-4b actually is

decider-4b v2, the open System One rebuild from Mapika, by Mapika.

decider is a family of open models from Mapika that reproduce the System One model class without generating text. The 4B model is Qwen3.5-4B-Base fine-tuned to read a state and a set of typed questions (choice over 2 to 255 options, score over 2 to 10 levels, and noul, the probability of yes) and to return one probability distribution per question from a single forward pass. It is Apache-2.0 and installs from PyPI as decider-ai. Its README states that it is not affiliated with TypeSafe and that nothing was distilled from Jev: the training mixture is public datasets plus data labelled by a local Qwen3.5-27B teacher.

Its server speaks TypeSafe’s /v1/systemone wire format, and the README says TypeSafe’s own SDKs work unchanged when pointed at it. The 4B model needs one CUDA GPU with about 8.4 GB in bf16, and the server captures its CUDA graphs at start-up. The package also runs on CPU, and Apple Silicon support covers the smaller dense models.

The version JevBench ranked is v2, released on 24 September: v1 plus a LoRA stage on harder decisions. The same day Mapika released v2.1, which recovers some game-playing ability but, by the author’s own measurement, is slightly weaker on JevBench’s public hard items and less well calibrated on them. If you want the model JevBench ranked, pin the Hugging Face tag v2.

What the benchmark disclosed about its training

JevBench records one disclosure from the author: 8,000 of the rows in the v2 training stage came from generators written from the published names of the ten sealed-question families, without reading any sealed item. The benchmark’s independent review judged the result legitimate, and notes that the author’s private second-stage training rows could not be audited for overlap with the public items.

Neither point means the score is wrong. They do mean decider-4b v2 was built after the sealed families were named, which is worth knowing when you read its sealed-set numbers.

Jev vs decider-4b FAQ

Other Jev comparisons

Every number on these pages is quoted from a published source and was read on October 9, 2026.

• Jev vs Imajev-4BA 4B model that reads photos, against the model it copies on text.
• Jev vs JevK5A fast open Qwen3.5-4B system, and far behind Jev on the answers.
• Jev vs CygnetNo training at all, thirteenth on the board, and behind Jev on every accuracy axis.
• Jev vs decisioFourth on the board on its biggest base, and it trains nothing of its own.
• Jev vs WinnowOne local model for decisions, chat and images, against a hosted decision model.
• Jev vs djevLevel with Jev when it was last measured, and more expensive to run.
• Jev vs SemIfA fast open rebuild on your own GPU, and where it still falls short.
• Jev vs OpenJevOne name, ten projects. Here is every one, and how the drop-in compares.
• Jev vs LayaA model you fine-tune on your data, against one that works out of the box.
• Jev vs Mercury DecideTwo hosted decision models that take the same request, two places apart.
• Run Jev locally?The open alternatives in one table, with licences and hardware.
• Jev vs LLMHow a decision model differs from a chat LLM and a BERT classifier.

Sources

• Benchmark Heaven — JevBench v1.6.1
• Mapika/decider — one-pass typed decisions (Apache-2.0)
• Mapika/decider-4b weights on Hugging Face
• TypeSafe documentation (Jev model card)