Jev vs Imajev-4B
Open Qwen3.5-4B decision model that also reads photos.
Jev 1.13.0
TypeSafe · System One model
63.3JevBench rank #4
Highest intelligence in the top ten: 53.1.
Imajev-4B
Mohit Garg · Open Qwen3.5-4B decision model that also reads photos
67.4JevBench rank #1
First of 91 on JevBench, with the best calibration in the top ten.
Key differences
- Where it runs JevHosted API, generally availableImajev-4BSelf-hosted on a Mac or one GPU
- Inputs JevText onlyImajev-4BText, plus up to two photos per request
- “Can’t tell” JevNot documented as a separate outputImajev-4BA trained unknown probability on every answer
- Evaluation-style cases Jev94.5% correctImajev-4B89.0% correct
- Sealed decisions Jev36.7% correctImajev-4B37.0% correct
- Calibration (JevBench) Jev76.3Imajev-4B80.4
- Input size Jev64k tokens per requestImajev-4BState up to 32 KB, about 8k tokens
JevBench v1.4.2.2, measured the same way
One benchmark measured 95 systems under one method and ranked 91, so these figures are comparable in a way vendor-published numbers are not. The composite weighs four axes — intelligence, calibration, speed and cost — and hides where systems actually differ, so the charts below break it apart. Full method at the source ↗
Composite score
The top four finish within 4.1 points of each other, then the board falls away sharply.
Capability, higher is better
Accuracy by how hard the decision is
Easy and standard decisions separate almost nothing. The hard tier is where these systems stop agreeing, and the sealed tier shows how much of that holds on questions nobody could have tuned for. A dash means the benchmark published no combined figure. The composite also weighs a fourth axis — cost — which we do not reproduce; see the source table.
What Imajev-4B is
Imajev-4B is an independent Apache-2.0 project by Mohit Garg: a Qwen3.5-4B LoRA that mirrors Jev’s /v1/systemone request contract and adds two things Jev does not have — image inputs (up to two photos per call) and a trained unknown_probability field so the model can abstain. Its author states no Jev outputs were used in training.
On JevBench v1.4.2.2 it entered at #1 with 67.4, ahead of Jev’s 63.3 on the composite — driven mainly by the best calibration in the top ten (80.4) and strong measured speed (90.6). Jev keeps the higher intelligence score (53.1 vs 52.2), a clear lead on judge-style cases (94.5% vs 89.0%), and the pair are level on the sealed set.
Where Imajev-4B falls short
- Without its calibration file the model is over-confident on hard items.
- An empty field can be read as “no” instead of unknown, and English is the only supported language.
- Its own image benchmark, ImajevBench, uses AI-generated images that have not yet had a human audit.
- State is limited to 32 KB (~8k tokens) — a sixth of Jev’s 64k-token request budget.
When to use which
Choose Jev if
- Your inputs are long text: documents, traces or tickets past about 8k tokens.
- Your hard cases turn on probabilities, reworded questions or multi-step lookups.
- You want a hosted, versioned model with nothing to serve.
Choose Imajev-4B if
- Your decisions depend on a photo: a listing against its picture, a return against what was shipped, a part against a known-good one.
- You want the model to say it cannot tell, and send those cases to a person.
- You need open weights that run on a Mac or one GPU inside your own network.
FAQ
Is Imajev-4B better than Jev?
On JevBench’s composite, yes: #1 at 67.4 against Jev’s #4 at 63.3, with better calibration and speed. Jev keeps a slightly higher intelligence score, 53.1 against 52.2, and a clear lead on the judge tier, 94.5% against 89.0%. On the sealed set they are level.
Can Imajev read images?
Yes. It takes up to two images per request — for example a reference and a target — alongside the state and questions. JevBench, which ranks it first, is a text-only benchmark and does not test that.
Is Imajev made by TypeSafe?
No. It is an independent Apache-2.0 project by Mohit Garg that mirrors Jev’s request contract. Its author states that no Jev outputs were used in training.
Do Jev requests work with Imajev?
Its README says text-only requests written for Jev’s /v1/systemone work unchanged, and the response adds unknown_probability and abstained fields. Check your state size against its 32 KB limit first.