Desk
Decision models like Jev return a choice, a score, or a yes/no.
Jev is TypeSafe AI's System One model. A program sends unstructured text and questions whose legal answers were listed in advance. The model returns a Choice, a Score, or a Noul. It does not write the answer out as text. What Jev is is the page for that call. Jev Day 2026 is the October 14, 2026 release of jev-1.14.0, plus opt-in images, a Box type, and 262k context. On October 16, at 08:19 UTC, one Box for every vehicle returned one rectangle, n = 3, and type array returned HTTP 400. TypeSafe's jev-latest still returned jev-1.13.0 at 00:28 UTC. Date headers 08:49:11 GMT to 08:49:40 GMT October 26, POSTs with jev-latest and jev-preview named jev-1.14.0. This page lists other hosted APIs and open checkpoints that publish the same kind of return. The figures are the ones already written up on this desk.
OR-decision-4B, posted October 30, 2026, prints JevBench 193 of 231, 83.55% on the card. The launch chart prints Choice 79.7 against Jev 79.6. Apache-2.0 LoRA on Qwen3.5-4B. This desk did not run the weights. MiniCPM5-2B-Jev, posted October 28, 2026, prints 78.79% on JevBench, first among open models at or under 2B, and decision-v7 86.41% with ECE 0.0307. Apache-2.0 on MiniCPM5-2B. This desk did not run the weights. BranchOne, posted October 29, 2026, returns Choice probabilities from Qwen3.5-0.8B-Base plus LoRA. Author A100 Colab median 0.305 s on ten short text questions. Apache-2.0. This desk did not run the weights. GLiDE v1.2, posted October 22, 2026, prints Decision Index 0.4.1 Full 71.5, rank 1 of 229, opened October 26. Docs $0.04 per million input tokens. GET /v1/models omitted GLiDE. POST /v1/systemone returned HTTP 401. Jeva-4B prints 0 flips on 600 Choice items. BANKING77 at K=16 is 91.62 against Jev 82.50. mammoth-1, posted October 21, 2026, prints Decision Index 0.4 Full 71.24 on the card. Opened October 26, the live space is edition 0.4.1, mammoth-1 Full 68.4 rank 3. Date headers 02:23:21 GMT to 02:23:23 GMT October 23, GET /v1/models with no key returned HTTP 401. d1-ultra, posted October 15, 2026, prints 65 on Artificial Analysis Decision Index against Jev 1.14 at 57, opened October 16. Vals AI, October 22, printed all 1,960 ClaimBench claims right. Liquid prices input at $0.042 per million tokens. This desk did not call that API. Celeris-1 Decision, posted October 8, 2026, prints 80.0% on 3,210 jev-bench items at a 67 ms median, and $0.04 per million input tokens. Opened October 16, Artificial Analysis Decision Index lists it at 52. GET /v1/models with no key returned HTTP 401. This desk did not send a billed POST. Span-02 prints Decision Index 0.3 text index 63.62 on its card, and thinking off at 61.2 against Jev 1.13.0 at 58.0 on the blog. This desk did not run the weights. kettei-fat, opened October 19, 2026, ranks first of 38 hosted systems on JevBench at composite 77.8. Docs price input at $0.06 per million tokens. GET /v1/models with no key returned HTTP 401. Drex Max, posted October 19, 2026, prints Decision Index 0.3.2 public 67.59 against Jev 1.14 at 60.70. Docs price input at $0.06 per million tokens. GET /v1/models with no key returned HTTP 401. Clairic, posted the same day, is Cloudflare's extraction model at $0.10 per million input tokens. It returns typed values, not a listed choice. Sieve-31B prints Decision Index 0.3.2 Full score 63.8. StartLux-Decision v1.1 27B Instant prints Full score 69.12, first of 174 on that board. basal-omni-1.0-ultra, posted October 17, ranks first of 184 open systems on Capability at 82.5. Apache 2.0, Gemma 4 31B. This desk did not run the weights. ToddlerJev, posted October 18, prints 68.70% on MMAU-mini under the Qwen Research License. pplx-decider-v1.2, posted October 16, prints Decision Index 0.3 overall 68.09 on joint requests, at $0.02 per million input tokens. OpenRouter Armor scored Jev 1.13 at 90.7% on 492 tool calls, 446 of 492. That plugin is not a catalog row. SubQ Snap 1.1 prints 65 on Artificial Analysis Decision Index, tied with d1-ultra and Elephant 9B. Docs name subq-snap-1.1 at $0.04 per million input tokens. Date headers 02:23:17 GMT to 02:23:20 GMT October 23, three POSTs from this desk returned HTTP 200. Quyet-1.0-Large's homepage prints Capability 81.7 on frozen JevBench v1.6.0, rank 1 of 92. Blink v0.3 prints 57.48 on a self-run of Decision Index 0.2.1, against the board's Jev cell of 57.91.
What is a decision model like Jev?
A decision model like Jev takes a state plus a fixed answer set and returns a probability for each allowed answer.
TypeSafe's three names are Choice, Score, and Noul. On Jev 1.14 a
Box returns four edges of an image. Choice picks
among named options. Score is a number on a rubric. Noul is a
yes/no probability from 0 to 1, with no separate confidence field.
Choice and Score include a confidence computed from the distribution.
Several questions can share one request. Open weights often serve
that shape at POST /v1/systemone. A hosted product
sometimes uses a different path and still documents the same three
types.
What is OpenAI's Decisions API?
On October 23, 2026, Date headers 02:23:12 GMT and 02:23:13 GMT, two POSTs from this desk to the Decisions API returned HTTP 200 from gpt-6-luna.
The September 29 posts say the call can send text or an image.
They are written up at
OpenAI's Decisions API.
A later page,
OpenAI Jev,
records Tibo Sottiaux on visual inputs and a chart The Decoder
opened from DevDay, labeled 150 ms for the Decisions API and 1.6 s
for the GPT-6 Luna API. That chart is The Decoder's. On October 6,
2026 OpenAI Developers posted public beta for all developers. The
guide, opened that day, prices gpt-6-luna input at
$0.10 per million tokens and lists no output charge. A POST to
https://api.openai.com/v1/decisions from this desk
returned HTTP 200, with 420 input tokens and 0 output tokens. The
choice and score answers included confidence. An empty POST returned
HTTP 400, missing model. Later the same day a cat sentence scored
0.98 on Decisions and on Jev, and a Stripe ticket was technical on
both, with confidence 0.99 and 0.74. October 2 and October 4 calls
had returned HTTP 403. The DevDay recap, opened October 6, still
said limited preview. The reference page returned HTTP 200.
OpenAI Developers posted general availability on October 22,
19:07 UTC. The guide, opened October 23, prices uncached input
at $0.10 per million tokens and cached input at $0.01, with no
output charge. Requests now hold up to 400 questions.
What is Cloudflare's Jev?
On October 9, 2026 Cloudflare's blog prices Clef-omni at $0.15 per million input tokens and Clef-flash at $0.038.
typesafe/jev on Workers AI is the hosted TypeSafe
model. Access records that card at 32,000 tokens. Clef and
Clef-flash are Cloudflare's Apache 2.0 decision models, posted
October 1, 2026, written up at
Clef.
The October 1 cards listed Clef-flash at $0.09 per million input tokens.
The October 9 blog lists $0.038, and lists Clef-omni at $0.15.
Clef-omni.
The October 1 docs print a 65,536-token window and up to four images.
The October 9 blog lists a hosted 24k window for Clef-flash.
The October 1 blog's median row is Clef 209.3 ms, Clef-flash 38.8 ms, and a
printed Jev cell of 524.1 ms. Fastino's October 3 chart prints
Clef at 61.2 and Clef-flash at 57.1 and captions those Cloudflare
scores as self-reported. The model card does not print that
composite.
What is SubQ Snap?
On October 23, 2026, Date headers 02:23:17 GMT to 02:23:20 GMT, three POSTs from this desk to SubQ Snap returned HTTP 200.
Docs name subq-snap-1.1 at $0.04 per million input
tokens, output free. GET /v1/models listed
subq-snap-1.1 and subq-snap-preview.
Artificial Analysis Decision Index prints Snap 1.1 at 65, tied
with d1-ultra and Elephant 9B. The October 12 blog prints Decision
Index 0.2.1 at 61.7 against a Jev cell of 57.9. On October 13, at
about 03:00 UTC, two POSTs returned HTTP 200, noul 0.98. The
write-up is
SubQ Snap.
What is d1-ultra?
Vals AI, October 22, 2026, 23:57 UTC, printed d1-ultra as the only decision model to get all 1,960 ClaimBench claims right.
Opened October 16, Artificial Analysis Decision Index prints 65
against Jev 1.14 at 57. Liquid's blog, posted October 15, prices
input at $0.042 per million tokens, output free. Model id
d1-ultra. POST
https://api.liquid.ai/decisions/v1/systemone. Vercel lists a
32,768-token window. This desk did not call the API. The write-up
is d1-ultra.
What is Celeris-1 Decision?
Celeris-1 Decision, posted October 8, 2026, prints 80.0% on 3,210 jev-bench items at a 67 ms median, and $0.04 per million input tokens.
Opened October 16, Artificial Analysis Decision Index lists it at 52.
Model id celeris-1-decision. POST
https://inference.celeris.ai/celeris-1-decision/v1/systemone.
GET /v1/models with no key returned HTTP 401. This desk did not send
a billed POST. The write-up is
Celeris-1 Decision.
What is Span-02?
Opened October 16, 2026, the Span-02 card prints Decision Index 0.3 text index 63.62.
The blog prints thinking off at 61.2 against Jev 1.13.0 at 58.0. Weights are a Gemma 4 26B-A4B fine-tune. This desk did not run them. The write-up is Span-02.
What is kettei-fat?
Opened October 19, 2026, JevBench ranks kettei-fat first of 38 hosted systems at composite 77.8.
ImageJevBench v0.3.0 capability is 75.9. Docs price kettei fat at
$0.06 per million input tokens. Model id kettei-fat.
POST https://api.sqwish.ai/v1/decide. GET /v1/models with no key
returned HTTP 401. This desk did not send a billed POST. The
write-up is kettei-fat.
What is basal-omni-1.0-ultra?
Opened October 19, 2026, JevBench ranks basal-omni-1.0-ultra first of 184 open systems on Capability at 82.5.
Composite among open weights is 71.8, rank 3. Apache 2.0, Gemma 4 31B. POST /v1/systemone on basal-serve. The card prints Werdykt v1 at 0.879. This desk did not run the weights. The write-up is basal-omni.
What is ToddlerJev?
ToddlerJev, posted October 18, 2026, prints 68.70% on MMAU-mini.
Weights are TeenageWorks/Toddler-Jev under the Qwen Research License. Base Qwen2.5-Omni-3B. This desk did not run them. The write-up is ToddlerJev.
What is OR-decision-4B?
alphaXiv posted OR-decision-4B on October 30, 2026, at 16:06 UTC. The Hugging Face card prints JevBench 193 of 231, 83.55%.
The launch chart prints Choice 79.7 against Jev 79.6, and sarcasm 53.6 against Jev 70.7. Apache-2.0 LoRA on Qwen3.5-4B, 117,186 train examples. Do not merge 83.55 with 79.7. This desk did not run the weights. The write-up is OR-decision-4B.
What is MiniCPM5-2B-Jev?
OpenBMB posted MiniCPM5-2B-Jev on October 28, 2026, at 13:01 UTC. The project prints 78.79% on JevBench, first among open models at or under 2B.
decision-v7 prints 86.41% accuracy with ECE 0.0307. Apache-2.0 on MiniCPM5-2B. Weights ytbai/MiniCPM5-2B-Jev. This desk did not run the weights. The write-up is MiniCPM5-2B-Jev.
What is BranchOne?
Necati Demir posted BranchOne on October 29, 2026. The open checkpoint returns one probability per supplied candidate from Qwen3.5-0.8B-Base plus LoRA.
His A100 Colab run prints median 0.305 s on ten short text questions. Apache-2.0. Weights ndemirdemir/BranchOne. No published JevBench score on the pages this desk opened. This desk did not run the weights. The write-up is BranchOne.
What is mammoth-1?
Base Labs posted mammoth-1 on October 21, 2026, at 17:14 UTC. The card prints Decision Index 0.4 Full 71.24, first of 208.
Opened October 23, the live space is edition 0.4.1, 229 models, mammoth-1 Full 68.4 rank 3. elephant-1 is the 9B sibling, card 62.65. MIT, from Qwen3.5-27B and Qwen3.5-9B. POST https://inference.baseten.co/v1/systemone. Date headers 02:23:21 GMT to 02:23:23 GMT, GET /v1/models with no key returned HTTP 401. The write-up is mammoth-1.
What is Drex Max?
Nace posted Drex Max on October 19, 2026. The product page prints Decision Index 0.3.2 public 67.59 against Jev 1.14 at 60.70.
Docs price input at $0.06 per million tokens. Model id
drex-max. POST https://console.nace.ai/v1/systemone.
Date headers 08:50:01 GMT and 08:50:02 GMT October 20, GET
/v1/models with no key returned HTTP 401. This desk did not send a
billed POST. The write-up is
Drex Max.
What is Clairic?
Cloudflare posted Clairic on October 19, 2026, a System One extraction model on Workers AI.
The blog's cascade ran in 19.3 s against 61.7 s for GLM-5.3 at
every step. Docs price input at $0.10 per million tokens. Hosted id
@cf/cloudflare/clairic. It returns typed values, not a
choice from a listed set. This desk did not call the API. The
write-up is Clairic.
What is Sieve-31B?
Sthānika's Sieve-31B card, opened October 20, 2026, prints Decision Index 0.3.2 Full score 63.8.
The authors' public-suite run is 62.52. Apache-2.0 LoRA on Gemma 4 31B. This desk did not run the weights. The write-up is Sieve-31B.
What is StartLux-Decision v1.1?
The StartLux-Decision README, opened October 20, 2026, prints v1.1 27B Instant at Full score 69.12, first of 174 on Decision Index 0.3.2.
The October 3 self-run of edition 0.2.1 stays 63.88. Weights are CC BY-NC 4.0. This desk did not run the weights. The write-up is StartLux-Decision.
What is pplx-decider-v1.2?
Perplexity posted pplx-decider-v1.2 on October 16, 2026, with Decision Index 0.3 overall 68.09 on joint requests against v1.1 at 62.30.
Docs price input at $0.02 per million tokens. Flash is $0.01. POST https://api.perplexity.ai/v1/decisions. GET of the OpenRouter ids returned HTTP 404. The write-up is pplx-decider.
Which other hosted APIs return a typed decision?
Levanto, Perplexity, Venice, Databricks, Liquid, Nace, Inception, Together, Fastino, Microsoft, TypeLLM, Subquadratic, Respan, Celeris, and Sqwish each document a hosted decision call. HAL-X documents THX-01 at POST https://api.hal-x.ai/v1/systemone. Access lists doors onto TypeSafe's Jev. The rows below are not all doors onto Jev.
| Call | Who | What the page prints |
|---|---|---|
| jev-1.13.0 | TypeSafe, POST /v1/systemone | $0.042 per million input tokens, output free, on the models page opened October 1, 2026. Pricing. |
| subq-snap-1.1 | Subquadratic, POST /v1/systemone | Docs, opened October 23: $0.04 per million input tokens, output free. Artificial Analysis Decision Index prints 65, tied with d1-ultra and Elephant 9B. Date headers 02:23:17 GMT to 02:23:20 GMT, three POSTs from this desk returned HTTP 200. GET /v1/models listed subq-snap-1.1 and subq-snap-preview. SubQ Snap. |
| Sage 1.3.0 | Levanto, hosted API | Opened October 11, 2026, the JevBench API board ranks this call first of 27 at composite 74.0. The pricing page lists Pro input at $0.042 per million tokens and output at $10 per million for reasoning. Sage. |
| THX-01 | HAL-X, POST /v1/systemone | The docs page names https://api.hal-x.ai. The October 11 post calls the API free. That page does not print a price. The card's ticket average is 98.4 against Jev 1.13 at 97.4 on 2,843 tickets. THX-01. |
| Decisions API | OpenAI, POST /v1/decisions | Generally available October 22. Date headers 02:23:12 GMT and 02:23:13 GMT October 23, two POSTs from this desk returned HTTP 200 from gpt-6-luna. Guide price $0.10 uncached, $0.01 cached, output uncharged. Up to 400 questions per request. OpenAI Jev. |
| Clef, Clef-flash | Cloudflare Workers AI | October 9 blog: Clef $0.24 and Clef-flash $0.038 per million input tokens. The October 1 cards listed Clef-flash at $0.09. October 1 medians stay 209.3 ms and 38.8 ms against a printed Jev cell of 524.1 ms. Clef. |
| Clef-omni | Cloudflare Workers AI | October 9 blog: $0.15 per million input tokens. BANKING77 macro-F1 94.8 on that post's ten-row table. A 21-second video with sound scores in about 1.5 seconds. Clef-omni. |
| pplx-decider-v1.2 | Perplexity, POST /v1/decisions | Posted October 16, 2026. Card Decision Index 0.3 overall 68.09 on joint requests against v1.1 at 62.30. Docs price input at $0.02 per million tokens, output free. Flash is $0.01. Opened October 7, v1.1 was 62.8 on the space. pplx-decider. |
| kettei-fat | Sqwish, POST /v1/decide | Opened October 19, 2026, JevBench ranks this call first of 38 hosted systems at composite 77.8. Docs price input at $0.06 per million tokens, output free. GET /v1/models with no key returned HTTP 401. kettei-fat. |
| jev-latest | Venice, POST /api/v1/decisions | Billed at TypeSafe's $0.042 rate on the September 18 post. Venice. |
| ai_decide | Databricks SQL and REST | Beta. Noul, choice, or score. Databricks posted October 16, 2026 that TypeSafe's Jev-1.14 is available through ai_classify and ai_decide. The September 30 blog does not name the checkpoint. The docs do not print a price. ai_decide. |
| span-02 | Respan, POST /api/v1/decisions | GET of the public models list, opened October 16, 2026, prints input_cost 0.01 and output_cost 0.0. The card's Decision Index 0.3 text index is 63.62. This desk did not call the API. Span-02. |
| d1-ultra | Liquid, POST /decisions/v1/systemone | Vals AI, October 22, printed all 1,960 ClaimBench claims right. Opened October 16, Artificial Analysis Decision Index prints 65 against Jev 1.14 at 57. Blog price $0.042 per million input tokens, output free. This desk did not call the API. d1-ultra. |
| celeris-1-decision | Celeris, POST /v1/systemone | October 8, 2026 blog: 80.0% on 3,210 jev-bench items, 67 ms median, $0.04 per million input tokens, output free. Opened October 16, Artificial Analysis Decision Index lists it at 52. GET /v1/models with no key returned HTTP 401. This desk did not send a billed POST. Celeris-1 Decision. |
| d1:free | Liquid, POST /decisions/v1/systemone | Output tokens always 0. An internal chart prints 58.9 against 57.9. Liquid d1. |
| Mercury Decide | Inception, on OpenRouter | Opened October 8, 2026, the JevBench API board ranks this call third at composite 72.4. The free model page returned the same day, priced Free, with up to 14 decisions a second and no JevBench score. Output tokens free. The September 30 post prints no score. The free model URL returned Not Found. Mercury Decide. |
| Microsoft-Decision-1 | Microsoft Foundry and OpenRouter | Command Line, October 9, 2026: $0.042 per million input tokens, output free. The post says 4.5 times quicker than Quyet-1.0-Large. Opened October 11, 2026, the JevBench API board ranks this call sixth of 27 at composite 69.1. The catalog, opened October 10, prints a 32,768-token window and says the weights are not distributed. Microsoft-Decision-1. |
| typellm-latest | TypeLLM, POST /v1/generate | Homepage, opened October 10, 2026: input $0.05 per million tokens, thinking $0.50 per million, typed answers free. The September 23 file scores Qwen3.8-27B at 228 of 231 public JevBench tasks with thinking. That file is not typellm-latest. TypeLLM. |
| Tev1-4B-experimental | Together, POST /v1/chat/completions | Opened October 7, 2026: $0.04 per million input tokens, output free. The call returns one letter. The September 23 post said $0.042. Tev1. |
| mammoth-1 | Baseten, POST /v1/systemone | Card Decision Index 0.4 Full 71.24. Opened October 23, live 0.4.1 Full 68.4 rank 3. Model decision-models/baseten-mammoth-27b-latest. Date headers 02:23:21 GMT to 02:23:23 GMT, GET /v1/models with no key returned HTTP 401. mammoth-1. |
| elephant-1 | Baseten, POST /v1/systemone | Card Decision Index 0.4 62.65. Live 0.4.1 Full 60.3. Artificial Analysis replica 65.2. Model decision-models/baseten-elephant-9b-latest. mammoth-1. |
| drex-max | Nace, POST /v1/systemone | Posted October 19, 2026. Product page Decision Index 0.3.2 public 67.59 against Jev 1.14 at 60.70. Docs $0.06 per million input tokens, output unbilled. Date headers 08:50:01 GMT and 08:50:02 GMT October 20, GET /v1/models with no key returned HTTP 401. Drex Max. |
| Drex 1.5 | Nace | The September 30 post prints $0.04 per million input tokens. Opened October 8, 2026, the product page prints no price. The chart still prints 199 of 231 against Jev at 201 of 231. The October 9 weights card prints Decision Index 0.3.1 public index 58.08 against Jev at 57.96. That index is not the September chart's 58.28. Drex. |
| fastino/GLiDE | Fastino, POST /v1/systemone | Opened October 26, 2026, Decision Index 0.4.1 Full 71.5, rank 1 of 229. Pricing lists $0.04 per million input tokens and $0 output. Date headers 08:49:09 GMT to 08:49:11 GMT, GET /v1/models omitted GLiDE, POST /v1/systemone HTTP 401. The October 8 reading was $0.15. The October 1 self-run of 64.81 stays. GLiDE. |
Which open-weight models return Choice, Score, or Noul?
The open checkpoints below publish weights and a typed decision. Repos lists the rest of the projects these stories cite, including servers that only wrap someone else's model.
| Checkpoint | License and base | One figure from its own page |
|---|---|---|
| GLiDE v1.2 | Fastino Community License. Modified Qwen3.8-27B. | Opened October 26, 2026, Decision Index 0.4.1 Full 71.5, rank 1 of 229. Hugging Face card fastino/GLiDE. This desk did not run the weights. GLiDE. |
| OR-decision-4B | Apache-2.0. LoRA on Qwen3.5-4B. | Card, opened October 31, 2026: JevBench 193 of 231, 83.55%. Launch chart Choice 79.7 against Jev 79.6. This desk did not run the weights. OR-decision-4B. |
| MiniCPM5-2B-Jev | Apache-2.0. MiniCPM5-2B. | Project: JevBench 78.79%, first among open models at or under 2B. decision-v7 86.41%, ECE 0.0307. This desk did not run the weights. MiniCPM5-2B-Jev. |
| BranchOne | Apache-2.0. Qwen3.5-0.8B-Base plus LoRA. | Author A100 Colab median 0.305 s on ten short text questions. Returns Choice probabilities. This desk did not run the weights. BranchOne. |
| Jeva-4B | Apache-2.0. Qwen3.5-4B. | Paper: 0 flips on 600 Choice items. BANKING77 at K=16 91.62 against Jev-1.13.0 at 82.50. This desk did not run the weights. Jeva. |
| Span-02 | Gemma 4 license (Apache 2.0). Gemma 4 26B-A4B, about 4B active. | Card, opened October 16, 2026: Decision Index 0.3 text index 63.62 on 140,178 requests. The blog prints thinking off at 61.2 against Jev 1.13.0 at 58.0. This desk did not run the weights. Span-02. |
| Quyet-1.0-Large | Apache-2.0. Gemma 4 31B. 31.3B on the card. | Homepage, opened October 12, 2026: frozen JevBench v1.6.0 official score 71.39, rank 1 of 92, Capability 81.7. Quyet. |
| Blink v0.3 | Apache-2.0 on the card. Gemma 4 26B-A4B. | Self-run of Decision Index 0.2.1 at 57.48, against the board's Jev cell of 57.91. Blink. |
| d3-ultra | Apache-2.0. Qwen3.8-27B. 26.09B on the card. | Opened October 26, 2026, Decision Index 0.4.1 Full score is 70.18, second of 229. The card's private SR-Text mean is 87.2. d3-ultra. |
| d3-turbo | Apache-2.0. Qwen3.8-27B. 26.09B on the card. | Opened October 26, 2026, Decision Index 0.4.1 Full score is 67.31. Vision full on edition 0.4 is 72.46, second of 56. The free API aliases vllm-sr/d3 to this model. d3-turbo. |
| d3 | Apache-2.0. Qwen3.8-27B. 26.09B on the card. | Opened October 26, 2026, Decision Index 0.4.1 Full score is 67.15. The October 16 card reading of edition 0.3.2 was 66.3. The free API now aliases this id to d3-turbo. Decision 3.0. |
| Mizan 4B | Apache-2.0. Qwen3.5-4B. | Mean accuracy 78.7 on 3,000 real Persian records, against the card's Jev cell of 83.7. Mizan 4B. |
| THX-01 | Apache 2.0. mmBERT-base, 322M. | Weights are public. Banking77 inside the card's 39-task suite is 65.9. The ticket average is in the hosted row. THX-01. |
| H2O-Lightning-4B v1.1 | Apache 2.0. Qwen3.5-4B, per the October 7 blog. | JevBench composite 72.5 against Jev 1.13.0 at 71.5, revision v1.7.17, 104 open-weight systems. H2O-Lightning-4B. |
| Drex v1.5 | Nace.AI Open RAIL-M. About 9B, from a Qwen3.5-9B distill. | Decision Index 0.3.1 public index 58.08 against Jev 1.13.0 at 57.96. Not Drex DLM's 52.31. Drex 1.5. |
| OpenBles Firewall 1 | MIT adapter. fastino/GLiNER2.5-Decide, Apache 2.0. | 119 of 120 agent attacks caught, and none of 120 benign look-alikes flagged. OpenBles Firewall 1. |
| Clef, Clef-flash | Apache 2.0. Qwen3.8-27B and Qwen3.5-9B. | Weights are public. The hosted prices are in the table above. Clef. |
| Clef-omni | Apache 2.0. Qwen3-Omni-30B-A3B-Instruct. | BANKING77 macro-F1 94.8 on the October 9 ten-row table. Clef-omni. |
| PurpleMIST-Flash-1.0 | Apache 2.0. Qwen3.5-9B-Base, text tower only. | 0.668 accuracy on 15,050 translated African-language decisions. PurpleMIST. |
| Vega 0.8B, vegaml | Apache 2.0. Frozen Qwen3.5-0.8B, plus a 4B. | 75.4% on 800 phishing emails, against Jev 1.13.0 at 61.9%. Not Decision 2.0's Vega. vegaml. |
| Open d1, d1-3B and d1-omni-600M | LFM Open License v1.0. LFM2.5-VL-3B and LFM2.5-Encoder-350M. | d1-3B card, Decision Index 0.2.1, 48.57, self-scored, not a board submission. The same table prints Winnow-12B at 50.02. Open d1. |
| Laya | Apache 2.0. Encoder, three checkpoints and a router. | JevBench 70.1. Banking77 0.425 against a published Jev 0.870. Laya. |
| Kev | Apache 2.0. LoRA plus a pointer head on Qwen. | Palmer's new-source table prints Kev-8B at 79.6% against Jev 85.7%. Kev. |
| Tev1 4B and 0.8B | Qwen3.5. The fine-tune license is still being finalized. Training scripts are MIT on Ollama's page. |
Ollama /v1/systemone. Mean on 3,880 decisions:
73.3% and 63.5%, against Nimble 75.7% and Jev 76.0%.
Tev1.
|
| pplx-decider-v1.2 | The card says a fine-tune of Qwen3.8-27B. The model API, opened October 17, 2026, lists license apache-2.0, private false, gated false. The README usage section still says the repository is private. Flash is a Qwen3.5-4B distill. | Card Decision Index 0.3 overall 68.09 on joint requests against v1.1 at 62.30. Vision 77.43 against 73.22. The October 8 space print of v1.1 at 62.8 stays that reading. pplx-decider. |
| Drex DLM |
CC BY-NC 4.0 weights. MIT code. Backbone NVIDIA
Efficient-DLM-8B. POST /v1/systemone.
| Decision Index 0.2 cell 52.31 against the kit's Jev cell of 51.67. Drex DLM. |
| PolicyLM-1.7B |
Apache-2.0. Fine-tune of BidirLM-1.7B-Embedding. A score from
0 to 1 for each category in a policy, up to 16. The card does
not serve Choice, Noul, or /v1/systemone.
| Custom-policy accuracy 0.842 at a 0.5 cutoff. The table has no Jev column. PolicyLM. |
| Bespoke Nimble 9B | LoRA on Qwen. The 324-row holdout is the author's labels. | 292 of 324 against Jev 1.13.0 at 302 of 324. Nimble. |
| imajev-4b | Apache 2.0. LoRA on Qwen3.5-4B. Up to two photos. | Opened October 8, 2026: JevBench v1.6.1 capability rank 31 at 61.9. Image JevBench v0.3.0 lists capability 68.0. imajev-4b. |
| Strands Decider 2B | Apache 2.0. 1.9 billion parameters. | 167 of 231 on the public tasks. Median 115 ms on an RTX 3090. Strands Decider. |
| NIRNAY 450M | Apache 2.0. Laya 421M plus about 30M. | phase_b is 0.8792 on 3,080 Banking77 rows. The Jev cell was not measured in that repo. NIRNAY. |
| WaterSheep | Apache 2.0. Fine-tune of ModernBERT-base. | 77.8% in distribution, 61.2% on held-out datasets. No Jev column. Adds multi-label. WaterSheep. |
| StartLux-Decision v1.1 27B Instant | Code Apache 2.0. Weights CC BY-NC 4.0. | README, opened October 20, 2026: Decision Index 0.3.2 Full score 69.12, first of 174. The October 3 self-run of edition 0.2.1 stays 63.88. StartLux-Decision. |
| mammoth-1 | MIT. Qwen3.5-27B. | Card, opened October 23: Decision Index 0.4 Full 71.24, first of 208. Live space 0.4.1 Full 68.4 rank 3. This desk did not run the weights. mammoth-1. |
| elephant-1 | MIT. Qwen3.5-9B. | Card Decision Index 0.4 62.65. Live 0.4.1 Full 60.3. Artificial Analysis replica 65.2. mammoth-1. |
| Sieve-31B | Apache 2.0. LoRA on Gemma 4 31B. | Hugging Face card, opened October 20, 2026: Decision Index 0.3.2 Full score 63.8. Authors' public-suite run 62.52. Sieve-31B. |
| basal-omni-1.0-ultra | Apache 2.0. Gemma 4 31B. | Opened October 19, 2026, JevBench Capability 82.5, first of 184 open systems. Werdykt v1 0.879 on the card. basal-omni. |
| basal-1.5 | Apache 2.0. Bielik base. 1.5B, 4.5B, and 11B. | Werdykt v1 macro 72.12%, against Jev 1.13.0 at 81.64%. basal-1.5. |
| ToddlerJev | Qwen Research License. Qwen2.5-Omni-3B. | MMAU-mini 68.70%. Posted October 18, 2026. ToddlerJev. |
| Decision 2.0 Vega | Apache 2.0. Six sizes. Vega is an adapter on Qwen3.8-27B. | Own Decision Index 0.2.1 run 56.5. The card does not print a Jev row. Decision 2.0. |
| Vela 2.0 | Apache-2.0. Four sizes. The 9B is a fine-tune of Decision-2.0-Lux-9B. The 0.3B tokenizer carries the Gemma Terms of Use. | 9B card, Decision Index 0.2.1, 41.63 with Noul calibration on. The default without that option is 41.09. The table does not print a Jev row. Vela 2.0. |
| fsdecide | README says MIT. 149M ModernBERT, trained on five app questions. | Review 91.3% of 80, against jev-latest at 56.3%. On the authors' general set, Jev is 90.5% and fsdecide is 60.5%. fsdecide. |
| JEV-27B-VL | Apache 2.0. Adapter on Qwen3.8-27B. Images. POST /v1/decide. | 15 of 20 pick-and-place scenes. Six-benchmark mean 84.07 against a hosted Jev cell of 83.85. That JevBench column is not the official board. JEV-27B-VL. |
| Open-Jev | Qwen3.5 LoRA plus a decision head. | Released 9B is 179 of 231 on the public tasks, against Jev at 200 of 231. Open-Jev. |
Do these scores belong on one board?
No. A Banking77 accuracy, a JevBench composite, and a Decision Index self-run are different tests, and a copied Jev cell is not a new measurement.
Compare places similar tests next to each other and keeps the caveat on the row. Evals collects the numbers with the sample the author printed. Jev benchmark is the JevBench board for TypeSafe's model, which is a separate ledger from the vendor tables above. TypeSafe's Master Customer Agreement section 2.3(f) forbids customers from publishing benchmarks of the Services. This desk reports published figures as published and does not rerun them.