On this site
Jev 1.13.0
TypeSafe · System One model
Ahead overall, and 23 points ahead on intelligence.
71.4JevBench v1.7.48 · Open-weights reference row · #15 of 48 on the API board · Capability #12
Jev comparison · JevBench v1.7.48 · updated October 31, 2026
Jev vs decider-4b
Level on speed, far behind on the answers.
vs
Alternative
decider-4b
Mapika · Open Qwen3.5-4B System One rebuild
#111 of 235 open-weights systems, from 8.4 GB of open weights, and the cheaper of the two to run.
43.1JevBench v1.7.48 · #111 of 235 on the open-weights board · Capability #89
- JevHosted API, generally availableWhere it runsdecider-4bSelf-hosted on one GPU, about 8.4 GB in bf16
- JevProprietary, hostedLicencedecider-4bApache-2.0 weights and package
- Jev91.2 · 0.24s median over the networkSpeeddecider-4b90.3 · 25ms raw on the benchmark’s GPU
- Jev63.6 on JevBenchIntelligencedecider-4b40.1 on JevBench
- Jev61.6Sealed decisionsdecider-4b35.0
- Jev50.3 above chanceYes/no questionsdecider-4b19.1 above chance
- Jev64k tokens per requestContextdecider-4b32k tokens
Try it on this page
Run Jev 1.14 right here
Edit the example or paste your own text, then run it. Sign in to run: new accounts get 20 welcome credits, and a failed run costs nothing.
Support ticket triage · Jev 1.14
1 Input
Hi, this is the third time I am writing. Our payouts have failed every day since Monday and my team cannot pay suppliers. I already re-entered the bank details twice. If this is not fixed today we will have to move to another provider.
2 Questions
- Choice Which team should handle this ticket?
- Yes / No Does the customer need a response today?
- Score How frustrated is the customer?
- Yes / No Does the customer threaten to leave or switch providers?
Which decider?
Mapika publishes several decider models, and releases come quickly. JevBench ranks five of them. This page compares Jev with decider-4b, the 4B model the family is known for; since 8 October the 12B models have been Mapika’s strongest entries, and they are in the table below.
decider-4b v2by Mapika
Qwen3.5-4B-Base, 4.2B parameters, about 8.4 GB in bf16. Released on 24 September; the version JevBench measured, kept under the Hugging Face tag v2. The model this page compares.
#111 of 235 at 43.1
decider-12b v2by Mapika
Gemma 4 12B fine-tuned the same way, added to the board on 8 October and now Mapika’s best result by a wide margin: intelligence 61.9, close to Jev’s 63.6, with a weaker calibration axis.
#27 of 235 at 73.7
decider-12b v1by Mapika
The first 12B release, read out of a stock Gemma 4 12B. Added on the same day and five tenths behind v2 on the composite.
#33 of 235 at 73.2
decider-4b v2.1by Mapika
The current default, released the same day: v2 plus a further LoRA stage. Its author reports it slightly weaker on JevBench’s public hard items, 0.649 against 0.676, and less well calibrated on hard items.
Not measured in JevBench v1.7.48
decider-35b-a3bby Mapika
Qwen3.5-35B-A3B-Base, 34.7B parameters with 3B active: about 65 GB in bf16 or 19.6 GB in NVFP4.
#80 of 235 at 66.5, held back by intelligence
decider-2bby Mapika
Qwen3.5-2B-Base, 1.9B parameters, about 4 GB. The first decider model, carried into the current board from an earlier measurement.
#180 of 235 at 8.0, held back by intelligence
decider chat on Gemma 4 31Bby Mapika
Not a decider model at all but an inference technique: Google’s Gemma 4 31B IT, frozen, read through Mapika’s decision prompt and readout. New in v1.6.1, and Mapika’s strongest entry until the 12B models were added.
#74 of 235 at 68.1
decider-0.8b and decider-2b-visionby Mapika
A smaller text model and a vision-language variant that reads decisions from pixels, still on older text weights.
Not measured in JevBench v1.7.48
JevBench v1.7.48, measured the same way
One benchmark measured every system under one method — it ranks 235 open-weights systems on one board and 48 hosted API offerings on another, with the same scores in both — so these bars are comparable with each other in a way that vendor-published figures are not. The full board and how to read it are on the JevBench results page.
Composite score
Plain numbers are ranks on the open-weights board; “API” marks a rank on the separate board for hosted API offerings. Jev, a hosted API, is ranked there, and appears on the open-weights board only as an unranked reference row, where its score falls between #49 and #50. The composite hides where systems actually differ, so the charts below break it apart. Benchmark Heaven’s headline Capability ranking, shown next to each score above, averages intelligence and calibration among Jev-class systems.
Capability, higher is better
IntelligenceHow often it picks the right answer, half from sealed decisions
CalibrationWhether 0.8 really means about 80%
SpeedMeasured response time
Intelligence on open and sealed decisions
Open300 decisions from public sources
Sealed1,200 private decisions nobody could tune for
By request type, chance-corrected
ChoicePick one of the options
NoulProbability that a statement is true
ScorePlace the case on a graded scale
The sealed half, highlighted, is where results cannot have been tuned: nobody outside the benchmark has seen those decisions. Request types are scored above chance, so 0 means guessing and a value below 0 means worse than guessing.
One thing these charts leave out: the composite score above also weighs a fourth axis, cost. We do not reproduce it here; the full table is at the source below.
Every system on the board
The capability scores are charted above; this is the ranking and the deployment detail behind them. Jev and decider-4b are highlighted.
| Model | Rank | Score | Measured latency | Runs on |
|---|---|---|---|---|
| H2O-Lightning-4B v1.1 (H2O.ai, Qwen3.5-4B) | #2 | 77.9 | 0.03s raw, 0.21s adjusted | Self-hosted GPU |
| Xor 26B-A4B (Juspay, Gemma 4 26B-A4B) | #21 | 74.0 | 0.06s raw, 0.27s adjusted | Self-hosted GPU |
| Arcbright Elf 1 31B | #23 | 74.0 | 0.06s raw, 0.27s adjusted | Self-hosted GPU |
| Quyet-1.0-Large (Chinh Nguyen, Gemma 4 31B decoder) | #25 | 73.8 | 0.12s raw, 0.39s adjusted | Self-hosted, H100 |
| Sage 1.3.0 (Levanto Labs, hosted API) | API #11 | 73.7 | 0.17s median / 0.41s p95 | Hosted API |
| decider-12b v2 (Mapika, Gemma 4 12B) | #27 | 73.7 | 0.05s raw, 0.26s adjusted | Self-hosted, RTX PRO 6000 |
| decisio v0.8.0 on Gemma 4 31B (Amin Roudaki, frozen base) | #32 | 73.2 | 0.05s raw, 0.24s adjusted | Self-hosted, H100 |
| decider-12b v1 (Mapika, stock Gemma 4 12B) | #33 | 73.2 | 0.05s raw, 0.26s adjusted | Self-hosted, RTX PRO 6000 |
| Mercury Decide (Inception, diffusion decision API) | API #14 | 72.2 | 0.34s median / 0.96s p95 | Hosted API |
| Winnow-12B Q8 (EldanRing, Gemma 4 12B) | #39 | 72.2 | 0.12s raw, 0.40s adjusted | Self-hosted, RTX 6000 |
| deck-31B (krishna765, frozen Gemma 4 31B) | #45 | 71.9 | 0.13s raw, 0.41s adjusted | Self-hosted GPU |
| Cygnet (blockbrain, frozen Gemma 4 12B) | #46 | 71.9 | 0.04s raw, 0.24s adjusted | Self-hosted, RTX PRO 6000 |
| Jev 1.13.0 (TypeSafe) | API #15 | 71.4 | 0.24s median / 0.31s p95 | Hosted API |
| Jev-Omni (akhilaaa3, Gemma 4 12B) | #52 | 71.0 | 0.16s raw, 0.47s adjusted | Self-hosted, RTX 6000 |
| decisio v0.8.0 on Gemma 4 12B (Amin Roudaki, frozen base) | #54 | 70.6 | 0.12s raw, 0.38s adjusted | Self-hosted GPU |
| torchcast-decision-12b (Torchcast AI, Gemma 4 12B) | #62 | 69.8 | 0.04s raw, 0.24s adjusted | Self-hosted, H100 |
| wity-1 (Wity, closed API, reasoning auto) | API #20 | 69.0 | 1.85s median / 7.97s p95 | Hosted API |
| Plumb-4B (crh225, JevK5 v0.2 + LoRA) | #96 | 50.4 | 0.02s raw, 0.19s adjusted | Self-hosted, H100 |
| decider-4b v2 (Mapika, Qwen3.5-4B) | #111 | 43.1 | 0.03s raw, 0.21s adjusted | Self-hosted, RTX 5090 |
| JevK5 v0.3 (allebee, Qwen3.5-4B) | #119 | 39.2 | 0.02s raw, 0.19s adjusted | Self-hosted, H100 |
| Imajev-4B (Mohit Garg, Qwen3.5-4B LoRA) | #133 | 30.0 | 0.07s raw, 0.29s adjusted | Self-hosted, RTX 5090 |
| Hopper (HopitAI, Qwen3.5-4B LoRA) | #136 | 27.7 | 0.06s raw, 0.26s adjusted | Self-hosted, RTX A6000 |
| SemIf (Qwen3.5-4B) | #160 | 16.1 | 0.06s raw, 0.27s adjusted | Self-hosted, RTX 5090 |
| Laya (ModernBERT-large) | #227 | 0.0 | 0.93s raw, 2.01s adjusted | Self-hosted, CPU |
JevBench method v1.7 applies a 10-second limit per decision: a response taking longer than 10 seconds counts as wrong and contributes zero calibration for that item. Speed uses all decisions, including failures. Benchmark Heaven re-scored recorded per-decision times; it did not run every model again. Tokens, draws and raw outputs are unchanged. Since method v1.8.0 (29 October 2026), self-hosted open-weights rows are costed by GPU time on a monthly-rented RTX PRO 6000 with an efficient inference engine instead of base-model list prices; encoders, architectures outside the six calibrated Gemma/Qwen classes and rows without a verified token basis keep their old costs, and API costs and both caps are unchanged. Intelligence, calibration and latency did not move, but most open-weights cost scores rose, so their composites rose and the Jev-class pool grew. Four rows recorded on a loaded CPU host await re-measurement and remain unranked with their dated v1.6 values; five CPU rows were measured again on GPU and replaced in full. The official composite combines intelligence, calibration, speed and cost using the frozen scorer. Each full-set system answers 1,500 decisions, 300 open and 1,200 sealed; most hosted APIs use an equated 600-item set. Half of intelligence comes from sealed decisions. The open-weights and API boards compare the same measurements within separate hosting groups. Board v1.7.48 ranks 235 open-weights systems and 48 API offerings; an additional API result is preliminary and unranked. There are 110 newer ranked open-weights rows tagged with their draw. Jev 1.13.0 remains an unranked reference on the open-weights board and is ranked on the API board. Capability averages intelligence and calibration among systems inside caps frozen at twice Jev’s v1.5 reference: 217 open-weights systems and 33 APIs qualify. The caps do not track current Jev latency. Self-hosted latency uses an estimated 2× measured latency plus 0.15s; API times include the network. Scores and splits on this site use method v1.8 (v1.7 scoring with the v1.8 cost basis); historical v1.6, v1.5 and v1.4 results are not current standings.
Jev and decider-4b feature by feature
| Attribute | Jev 1.13.0 | decider-4b |
|---|---|---|
| What it is | Hosted System One model from TypeSafe, version jev-1.13.0 | Open-weight Qwen3.5-4B-Base fine-tuned for one-pass typed decisions |
| Licence | Proprietary, hosted | Apache-2.0 for weights and package |
| Request format | POST /v1/systemone | The same wire format; TypeSafe’s SDKs work with a changed base URL |
| Question types | Noul, choice, score — many per call, answered in parallel | Noul, choice up to 255 options, score over 2–10 levels — one answer slot per question in one pass |
| Context | 64k tokens per request | 32k tokens |
| Languages | Best in English; other languages work with lower accuracy | English only |
| Calibration | Post-trained with RLCD; JevBench 90.6 | One fitted temperature, 1.935 in the measured build; JevBench 89.6 |
| Hardware | None — it is an API call | One CUDA GPU, about 8.4 GB in bf16; also runs on CPU |
| Version measured | jev-1.13.0 | v2, kept under the Hugging Face tag v2; v2.1 is now the default |
What each one is better at
Where Jev wins
- Intelligence 63.6 against 40.1, and 61.6 against 35.0 on the sealed half.
- Yes/no questions 50.3 above chance against 19.1, and score questions 63.2 against 36.3.
- Open and sealed results two points apart; decider-4b’s gap is about four times the field median.
- Twice the context, 64k tokens against 32k, and usable beyond English.
- Nothing to operate, and one stable hosted version rather than a model with three releases between 22 and 24 September.
Where decider-4b wins
- #89 on the Capability ranking in JevBench v1.7.48, well above its #111 on the official score, because that ranking leaves speed and cost out.
- Speed 90.3 against 91.2, from a 25ms raw median per decision on the benchmark’s RTX 5090, and a better cost score, 79.1 against 54.7.
- Apache-2.0 weights, with the training code and the builders for its public datasets in the repository.
- Speaks TypeSafe’s wire format, so moving a Jev integration is a base-URL change.
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 external check before listing it first found the result legitimate. On the re-measured v1.6 pool it is #111 of 235 open-weights systems at 43.1, against 71.4 for Jev, which the board shows as an unranked reference. Where it still holds up is the two cheap axes: speed 90.3 against Jev’s 91.2, from a raw median of 25ms per decision, and the benchmark’s cost estimate for a 4B model, 79.1 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 43.1 while its individual axes look respectable.
So the official score and the Capability ranking disagree, and both are honest: decider-4b is #111 on the score but #89 in the Capability ranking, 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 external 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.
So which should you use?
Pick Jev if
- The decisions that matter are the hard ones: long policies with exceptions, multi-hop lookups, questions reworded by different people.
- Inputs run past 32k tokens, or are not in English.
- You want a hosted, versioned model with published rate limits and nothing to serve.
Pick decider-4b if
- You already run GPUs and want millisecond decisions on your own hardware.
- Most of your decisions are routine, where the two are close, and volume makes per-decision cost matter.
- You need open weights for offline use, data residency or fine-tuning.
Try Jev on the cases you are actually arguing about
decider-4b is close enough, and fast enough, that the honest test is your own cases. Run them on Jev here with no setup and keep the answers: if decider-4b agrees where it matters, you have a strong case for self-hosting, and if it does not, you will see exactly which cases it misses.
Jev vs decider-4b FAQ
Is decider-4b better than Jev?
Not in the current benchmark. JevBench v1.7.48 ranks decider-4b #111 of 235 open-weights systems at 43.1; Jev, shown there as an unranked reference, scores 71.4. decider-4b is cheaper to run but scores slightly lower on speed; Jev is far ahead on intelligence, 63.6 against 40.1, and on the sealed half, 61.6 against 35.0. In v1.4.2 decider-4b was briefly first.
Is decider made by TypeSafe?
No. It is a third-party Apache-2.0 project by Mapika. Its README states that it is not affiliated with or endorsed by TypeSafe AI and that nothing was distilled from Jev.
Can I point the TypeSafe SDK at decider?
Yes, according to its README: the server implements POST /v1/systemone in TypeSafe’s wire format, so the SDKs work once their base URL points at your server. Check your input lengths against its 32k-token context first.
Which decider version does JevBench rank?
decider-4b v2, released on 24 September and still available under the Hugging Face tag v2. The current default, v2.1, was released the same day and was not measured on the v1.6 pool; its author reports it slightly weaker on JevBench’s public hard items.
What about decider-2b and decider-35b-a3b?
Both are ranked in JevBench v1.7.48: decider-2b at #180 with 8.0, held back by intelligence, and decider-35b-a3b at #80 with 66.5, held back by intelligence just under the benchmark’s floor of 50. Mapika’s strongest models are the 12B pair added on 8 October, #27 and #33 on the open-weights board at 73.7 and 73.2, both above Jev’s 71.4 reference score; both come close to Jev on intelligence and stay well behind it on calibration.
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 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 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, 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
decider-4b and every other product named on this page belongs to its respective owner and is not affiliated with Jev AI. Figures are quoted from the sources above as they read on October 31, 2026 and can change.