Jev vs SemIf

The analysis

Where Jev and SemIf really differ, and why the bars above land where they do.

SemIf is #160 of 235 open-weights systems in JevBench v1.7.48 at 16.1, against 71.4 for Jev, which the board shows as an unranked reference; in v1.5.6 it was #14, and the full re-measure on the new pool moved it down sharply. What standing it keeps comes from speed and cost: 90.4 on speed, a shade behind Jev’s 91.2, and the benchmark’s cost estimate for a frozen 4B model is low, 77.6 against Jev’s 54.7. If somebody tells you open models cannot do typed decisions cheaply, SemIf is still a counterexample.

On the answers the gap is wide and has widened. Intelligence is 63.6 against 27.1, and on the sealed half 61.6 against 23.8. By request type Jev leads everywhere: choice 77.4 against 47.6 above chance, score 63.2 against 25.3, and yes/no 50.3 against 8.3, where SemIf is barely above guessing. Calibration is closer, 90.6 against 83.6, but SemIf reads conditional probabilities off a frozen model rather than being post-trained to make them honest, and its own README asks you to calibrate per workload.

The other gap is not in the model at all. Self-hosting SemIf means keeping a GPU serving stack running, and bursty traffic leaves that GPU idle between peaks — and somebody on your team now owns the stack.

What SemIf actually is

SemIf, formerly OpenJev, from TheoLeeCJ, by TheoLeeCJ.

SemIf takes three things: an unstructured state, criteria you write at request time, and a set of typed options. It runs one forward pass through an open model and reads the native logits for the option tokens. Because nothing is generated, there is no answer sentence to parse and no malformed JSON to retry. The project is explicit that it reproduces Jev’s interface, not Jev’s undisclosed model or training.

It runs on Qwen3-0.6B, MiniCPM5-2B, Qwen3.5-4B (the primary baseline and the configuration JevBench measured) and Qwen3-Reranker-4B. The code is MIT; the model weights keep their own upstream licences. There is a WebGPU browser demo, and deployment is self-hosted only — there is no SemIf service to call.

The speed argument is the strongest part of the project. On an RTX 3090 with a frozen state and 21 binary criteria, reading typed logits directly takes 1.023 seconds against 5.332 seconds to generate the same JSON array. With parallel suffix reuse the author measures 20.03 decisions per second against 2.33 for the autoregressive path.

On accuracy the author is careful rather than promotional: on a 102-row subset of TypeSafe’s cases, direct logits reach 0.845 modal agreement against Jev’s published 0.883, and balanced accuracy on authored decisions is 0.813. The README notes that this covers 102 aligned rows, not TypeSafe’s full 711-row aggregate.

A note on the name

SemIf was previously called OpenJev, and you will still find the old name in benchmark tables and blog posts. It is not the same project as openJev Verdict, openjev-sglang or the other repositories carrying that name — those are separate efforts by different authors. We untangle all of them on the Jev vs openJev page.

Jev vs SemIf FAQ

Other Jev comparisons

Every number on these pages is quoted from a published source and was read on October 31, 2026.

• Jev vs Imajev-4BA 4B model that reads photos, against the model it copies on text.
• Jev vs decider-4bLevel on speed, far behind on the answers.
• Jev vs JevK5A fast open Qwen3.5-4B system, and far behind Jev on the answers.
• Jev vs CygnetNo training at all, forty-sixth on the open-weights board, and behind Jev on every accuracy axis.
• Jev vs decisioTenth on Capability on its biggest base, and it trains nothing of its own.
• Jev vs metask-jev-rainMore accurate answers than Jev on the benchmark, and two of three rows above it on the composite.
• 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 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, one place 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 board v1.7.48 (open weights)
• Benchmark Heaven — JevBench API board
• SemIf — semantic ifs from open models (MIT)
• TypeSafe documentation (Jev model card)