newly added

Multimodal decision family from the PlayJev authors: calibrated probabilities over screenshots, photos, video, and text in one forward pass, in 0.8B / 4B / 9B / 27B sizes. Apache 2.0 weights plus a Hugging Face dataset, with published comparisons against Jev 1.13 and Jev-Omni.

github.comPythonApache-2.0pushed oct 1317 forksadded oct 13

The Strands Agents org's open decision-model family (weights live under Hugging Face's amazon org too): four Gemma 4 builds from E2B to 26B-A4B, each answer carrying a calibrated reliability score, with JevBench, Brier, and Decision Index numbers published per size. Apache 2.0, ships a CLI.

github.comPythonApache-2.0pushed oct 1279 forksadded oct 13

HIT-TMG's recipe for turning an embedding model into a decision model: choice / score / noul heads over your pick of embedder, with a Hugging Face model collection and dataset. Apache 2.0.

github.comPythonApache-2.0pushed oct 125 forksadded oct 13

Open-weight Jev alternative (4B and 9B, Apache 2.0) serving /v1/systemone at about 13 ms on an H100. JevBench v1.4 ranked v0.2 second of 76 systems and first open entrant, though the project itself reports Jev edging it on 308 fresh sealed items. Two-teacher distillation, pre-registered epoch sweeps.

github.comPythonApache-2.0pushed sep 2812 forksadded oct 13

Recursively self-improving research loop that trains the models: AI agents propose hypotheses, register predictions before spending GPU time, and retire their own champions on the evidence. Eight releases in 13 days, 496 published experiments including failures; v6.1-VL 27B posts 65.64 on the Decision Index 0.3 public set, the top listed score. MIT code, Apache 2.0 weights, Jev-compatible API.

github.comHTMLMITpushed oct 109 forksadded oct 13

Local-first social-media research agent for Instagram, TikTok, and LinkedIn: Jev picks each next operation (search, open a post or profile, read comments, finish), a local CLI executes it in your signed-in Chrome, and every observed result goes back to Jev. Source-cited reports, no account credentials leave the machine.

github.comJavaScriptMITpushed oct 1237 forksadded oct 13

Prebuilt agents that run a System 1 model (Jev, Laya, or Cua-S1) as the brain across browser use, computer use, robotics, and games, with Claude Code or Codex scaffolding new ones. Publishes per-scenario timings: up to 6× faster and 25× cheaper than a chat model at the same score.

github.comPythonApache-2.0pushed oct 1322 forksadded oct 13

The LM Studio of decision models, from Bud Ecosystem: a cross-platform desktop app that checks your hardware, pulls Jev-like models, and serves them locally. Give a model a situation and typed questions, get calibrated probabilities in milliseconds.

github.comHTMLpushed oct 95 forksadded oct 13

Provider-neutral System One runtime for TypeScript and Pi: write the choice / noul / score decision once behind a SystemOneProvider interface, run it on Jev, Reflex, or any compatible /v1/systemone endpoint.

github.comTypeScriptpushed oct 86 forksadded oct 13

Subquadratic's long-context decision model: multimodal input with a 384K context (versus Jev's 32K) on a proprietary subquadratic sparse-attention stack. Their runs beat Jev on long-context retrieval (Decision LCR 74 vs 48) and on 13 of 16 enterprise suites by +6.0 on average, while still trailing on When2Call. $0.05/M input, output free.

subq.aiadded oct 12

Nace.AI's open decision models: v1.5 on a distilled Qwen3.5-9B and DLM on an Efficient-DLM-8B diffusion backbone, each serving /v1/systemone three ways: Python/vLLM, a llama.cpp GGUF fork, or Ollama.

github.comPythonApache-2.0pushed oct 133 forksadded oct 12

SberAI's Russian-first encoder decision model: choice / score / noul plus a ranking question type, all questions scored in one packed encoder pass with an exact state cache. Torch, int8 ONNX, MLX, or vLLM.

github.comPythonpushed oct 102 forksadded oct 12

Small trained decision models on Qwen3.5 (0.8B and 4B) serving /v1/systemone at ~50 ms on one H100. jiwo-0.8b ranks #1 of 27 under 1B on the Decision Index board; both models are on the board. Apache 2.0.

github.comPythonMITpushed oct 10added oct 12

Largha-150M: a 144M bilingual decision model on mmBERT-small (English-first, Chinese evaluated on translated cases). Calibrated noul / choice / score answers robust to option reordering, one pass per decision.

github.comPythonApache-2.0pushed oct 13added oct 12

Typed decisions from a frozen LM plus a small physics engine, from Laya's author: calibrated probabilities, conformal answer sets, and an explicit abstain flag. 800M or 4B, 73K context, image inputs.

github.comPythonApache-2.0pushed oct 1125 forksadded oct 12

Calibrated judge in front of a frontier model: a small local model answers routine decisions under a distribution-free bound on disagreement; everything else escalates, and each escalation teaches the judge further. Includes an MCP server.

github.comPythonApache-2.0pushed oct 11added oct 12

Simon Willison's llm plugin for the OpenAI Decisions API: evaluate text and images with predicates, choices, and scores.

github.comPythonApache-2.0pushed oct 61 forksadded oct 12

68 pretrained logistic-regression classifiers that run and retrain on CPU: banking77 at 94.3%, CLINC-OOS, spam, plus game-state deciders for Doom and poker. The "do you even need a decision model" baseline; pip package with a live playground. MIT.

github.comPythonMITpushed oct 132 forksadded oct 11

Nish Tahir (2026). The clearest mechanism explainer yet: constrained option tokens and a softmax over answer letters versus autoregressive JSON generation, with an interactive demo, working Qwen code, and an honest note that raw token probabilities are not calibrated confidence.

nishtahir.comadded oct 11

ZooWork's hosted decision model in two tiers: a Qwen3.8-27B build and a cheaper dual-4B. Ranks #9 of 27 on JevBench's hosted board; the base is operator-reported and weights are closed.

zoowork.aiadded oct 10

Levanto Labs' hosted decision model. Currently #1 on JevBench's hosted composite (74.0 vs Jev's 71.5), winning on speed and cost rather than raw intelligence. Closed API.

levanto.aiadded oct 10

SurdAI's hosted decision system (Flash and Pro tiers): a router/cascade on the /v1/systemone shape rather than a single model. Flash ranks #7 on JevBench's hosted board.

surd.aiadded oct 10

Alphanimble's hosted decision model with an auto-reasoning mode. Ranks #5 on JevBench's hosted board, above Jev on the composite. Closed API.

wity.alphanimble.comadded oct 10

Audio-decision counterpart to Image JevBench, for the multimodal entrants (Clef-omni, d1-omni, NeuDecide).

benchmarkheaven.comadded oct 10

Independent decision-model leaderboard (run by Benchmark Heaven, not TypeSafe): 1,500 typed decisions per system scored on intelligence, calibration, latency, and cost, with versioned releases, published methodology, and result JSON. Two boards — open weights and hosted API — across ~75 systems; the hosted board currently ranks Sage #1, d1 #2, Mercury Decide #3, Jev #4.

benchmarkheaven.comadded oct 10

Open five-size family (Tiny to a 31B Large) on Gemma 4: merged LoRA plus a letter-readout decision prompt with fitted temperatures. TypeSafe /v1/systemone answers via the quyet Python package; English and Vietnamese, Apache 2.0, GGUF builds. The speed runner-up in Microsoft's Decision-1 benchmark post.

hugging face modelpushed oct 101.1k downloadsadded oct 9

Microsoft's decision-scoring model: Qwen3.5-9B post-trained for single-pass choice/noul/score plus rubric grading, calibrated probabilities over a fixed answer set. Microsoft's 36-benchmark, ~150K-question blind eval claims top accuracy and fastest measured (~35× faster than GPT-6 Sol), with a 1.3% flip rate under input perturbations. Live in Microsoft Foundry; OpenRouter planned. Already used internally by Xbox Research and Copilot.

commandline.microsoft.comadded oct 9

OpenAI's entry in the class, announced at DevDay 2026: text or image context plus a fixed answer set, returning one answer with a confidence score around 150–230 ms. Powered by a Luna variant. Also routable on OpenRouter as openai/gpt-6-luna-decisions.

developers.openai.comadded oct 9

Trace mining for post-training: reads agent traces (OTel, Langfuse, Claude Code), judges each step by the tool's reaction rather than the agent's claim, distills the LLM judge into deterministic Python checks a human signs off on, and exports labeled SFT rows with full lineage. Its bundled Jev recipe trains a decision model on those labels with an honest scorecard — their Qwen3.5-4B reports 79.1% vs Jev's 66.8% on 1,920 held-out AgentProcessBench steps.

github.comPythonpushed oct 137 forksadded oct 8

Independent reproduction of Jev-style post-training on MiniCPM5-2B via LoRA: 51% → 80.5% on a sealed, leakage-checked holdout for about $5 of compute. Stage 1 covers single-letter choice only; the rigor is the point — significance testing, baselines, and a technical report that voids its own figure after finding contamination. MIT.

github.comPythonMITpushed oct 12added oct 8

KR Labs × vLLM Semantic Router's open decision-model family (0.3B–9B, bidirectional ModernBERT encoder, 17 languages, Apache 2.0). Choice, Noul, and Score plus two new question types: Span — labeled text spans with offsets for PII and unsupported claims — and Set multi-label. SystemOne-compatible HTTP and Python APIs, ONNX runtime, and a Core ML port with a Swift runtime for Apple silicon. Trained for router work: routing, prompt-attack, PII, and hallucination screening.

hugging face modelpushed oct 72.2k downloadsadded oct 8

Open, programmable decision layer for models and compute: routes requests across models, enforces safety checks, and picks reasoning effort — with the Vela decision models as its routing brain. Apache 2.0.

github.comGoApache-2.0pushed oct 131k forksadded oct 8

Neuphonic's ~40 MB voice-action model: speech in, an action decision out, running entirely on WebAssembly in the browser. From the neuTTS/neucodec audio lab; model repo is gated, the Space is the public demo.

hugging face spaceotherpushed oct 8added oct 8

Liquid AI's open decision-model family: d1-3B (text + vision, from LFM2.5-VL) and d1-omni-600M (adds audio). Single forward pass; d1-3B scores 48.57 on the Decision Index public split — best under 10B, on par with Decider 35B-A3B at 12× its size — at ~8 ms on an RTX 4090, 16 ms on Jetson AGX Thor. Open weights and GGUF builds on Hugging Face; also hosted on OpenRouter, where it ranks #2 on JevBench's hosted board.

liquid.aiadded oct 8

Perplexity's decision model (Decider V1.1 27B is the current checkpoint), on the System One request shape. On OpenRouter.

openrouter.aiadded oct 8

TypeSafe's meta-application of Jev: a model that picks the best model and reasoning effort for each request, balancing quality, speed, and cost.

openrouter.aiadded oct 8

Inception's structured decision model on the System One schema, from the diffusion-LLM lab behind Mercury. A free route exists on OpenRouter. Ranks #3 on JevBench's hosted board.

openrouter.aiadded oct 8

Train-your-own multimodal System One model: evaluates text, images, and video against task instructions and returns probabilities over supplied candidates. Ships the model code, data pipeline, SFT plus experimental RLCD training, and evals.

github.comJupyter NotebookApache-2.0pushed oct 1371 forksadded oct 8

Ollama for decision models: ollaya pull / serve / run manage Laya, decider, NLI, and GLiClass locally behind a wire-identical TypeSafe /v1/systemone (and /v1/decisions) endpoint.

github.comRustApache-2.0pushed oct 1379 forksadded oct 8

Intent compiler that converges vague requests into typed IntentSpec contracts — probe, ask, or halt — before routing. The input layer in front of routers and decision models like Jev or Laya.

github.comPythonMITpushed oct 1157 forksadded oct 8

Run Laya from Node.js / TypeScript via ONNX Runtime; the ~1.7 GB weights download from Hugging Face on first use.

github.comTypeScriptMITpushed sep 2176 forksadded oct 8

AI2's grade-school science MCQs in Easy and Challenge splits. Part of the standard MCQ battery used in Jev vs Luna Decisions comparisons.

allenai.orgadded oct 7

Graduate-level, Google-proof MCQs; the Diamond subset is the hard tier. Part of the standard MCQ battery used in Jev vs Luna Decisions comparisons.

github.comJupyter NotebookMITpushed sep 30 202460 forksadded oct 7

Grade-school math word problems; repurposed as multiple choice with random distractors (4- and 10-option conditions in the Jev vs Luna comparison).

github.comPythonpushed jan 21 2024203 forksadded oct 7

Commonsense sentence-completion MCQs. Part of the standard MCQ battery used in Jev vs Luna Decisions comparisons.

rowanzellers.comadded oct 7

The standard 57-subject multitask MCQ benchmark. Part of the standard MCQ battery used in Jev vs Luna Decisions comparisons.

github.comPythonMITpushed may 28 2023122 forksadded oct 7

Harder MMLU successor with 10-option questions and more reasoning. Part of the standard MCQ battery used in Jev vs Luna Decisions comparisons.

github.comPythonApache-2.0pushed mar 1858 forksadded oct 7

Multistep soft-reasoning MCQs (murder mysteries, object placements, team allocation). Part of the standard MCQ battery used in Jev vs Luna Decisions comparisons.

github.comPythonMITpushed aug 10 202413 forksadded oct 7

Pronoun-resolution commonsense MCQs, adversarially filtered. Part of the standard MCQ battery used in Jev vs Luna Decisions comparisons.

winogrande.allenai.orgadded oct 7