Entries newly added to the System One Models list.https://system-one-models.com/https://system-one-models.com/entry/onejev/https://system-one-models.com/entry/onejev/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.Tue, 13 Oct 2026 12:37:47 GMTModelshttps://system-one-models.com/entry/strands-decider/https://system-one-models.com/entry/strands-decider/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.Tue, 13 Oct 2026 12:37:47 GMTModelshttps://system-one-models.com/entry/jevembed/https://system-one-models.com/entry/jevembed/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.Tue, 13 Oct 2026 12:37:47 GMTOpen Implementationshttps://system-one-models.com/entry/jevk5/https://system-one-models.com/entry/jevk5/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.Tue, 13 Oct 2026 12:37:47 GMTOpen Implementationshttps://system-one-models.com/entry/rsi-jev/https://system-one-models.com/entry/rsi-jev/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.Tue, 13 Oct 2026 12:37:47 GMTOpen Implementationshttps://system-one-models.com/entry/jev-social/https://system-one-models.com/entry/jev-social/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.Tue, 13 Oct 2026 12:37:47 GMTAgentshttps://system-one-models.com/entry/system1-agents/https://system-one-models.com/entry/system1-agents/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.Tue, 13 Oct 2026 12:37:47 GMTAgentshttps://system-one-models.com/entry/bud-decision-studio/https://system-one-models.com/entry/bud-decision-studio/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.Tue, 13 Oct 2026 12:37:47 GMTToolshttps://system-one-models.com/entry/iamaamir-system-one/https://system-one-models.com/entry/iamaamir-system-one/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.Tue, 13 Oct 2026 12:37:47 GMTSDKs & Adaptershttps://system-one-models.com/entry/subq-snap/https://system-one-models.com/entry/subq-snap/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.Mon, 12 Oct 2026 22:03:05 GMTModelshttps://system-one-models.com/entry/drex/https://system-one-models.com/entry/drex/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.Mon, 12 Oct 2026 06:01:52 GMTOpen Implementationshttps://system-one-models.com/entry/frida-decisions/https://system-one-models.com/entry/frida-decisions/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.Mon, 12 Oct 2026 06:01:52 GMTOpen Implementationshttps://system-one-models.com/entry/jiwo/https://system-one-models.com/entry/jiwo/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.Mon, 12 Oct 2026 06:01:52 GMTOpen Implementationshttps://system-one-models.com/entry/phocinae/https://system-one-models.com/entry/phocinae/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.Mon, 12 Oct 2026 06:01:52 GMTOpen Implementationshttps://system-one-models.com/entry/vegaml/https://system-one-models.com/entry/vegaml/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.Mon, 12 Oct 2026 06:01:52 GMTOpen Implementationshttps://system-one-models.com/entry/kadi/https://system-one-models.com/entry/kadi/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.Mon, 12 Oct 2026 06:01:52 GMTToolshttps://system-one-models.com/entry/llm-openai-decisions/https://system-one-models.com/entry/llm-openai-decisions/Simon Willison's llm plugin for the OpenAI Decisions API: evaluate text and images with predicates, choices, and scores.Mon, 12 Oct 2026 06:01:52 GMTSDKs & Adaptershttps://system-one-models.com/entry/jeffy/https://system-one-models.com/entry/jeffy/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.Sun, 11 Oct 2026 08:47:58 GMTBaselineshttps://system-one-models.com/entry/build-your-own-decision-model/https://system-one-models.com/entry/build-your-own-decision-model/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.Sun, 11 Oct 2026 08:47:58 GMTReadinghttps://system-one-models.com/entry/instinct/https://system-one-models.com/entry/instinct/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.Sat, 10 Oct 2026 13:22:54 GMTModelshttps://system-one-models.com/entry/sage/https://system-one-models.com/entry/sage/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.Sat, 10 Oct 2026 13:22:54 GMTModelshttps://system-one-models.com/entry/spx-cd/https://system-one-models.com/entry/spx-cd/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.Sat, 10 Oct 2026 13:22:54 GMTModelshttps://system-one-models.com/entry/wity-1/https://system-one-models.com/entry/wity-1/Alphanimble's hosted decision model with an auto-reasoning mode. Ranks #5 on JevBench's hosted board, above Jev on the composite. Closed API.Sat, 10 Oct 2026 13:22:54 GMTModelshttps://system-one-models.com/entry/audiojevbench/https://system-one-models.com/entry/audiojevbench/Audio-decision counterpart to Image JevBench, for the multimodal entrants (Clef-omni, d1-omni, NeuDecide).Sat, 10 Oct 2026 13:22:54 GMTBenchmarkshttps://system-one-models.com/entry/jevbench/https://system-one-models.com/entry/jevbench/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.Sat, 10 Oct 2026 13:22:54 GMTBenchmarkshttps://system-one-models.com/entry/quyet/https://system-one-models.com/entry/quyet/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.Fri, 09 Oct 2026 19:26:29 GMTModelshttps://system-one-models.com/entry/microsoft-decision-1/https://system-one-models.com/entry/microsoft-decision-1/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.Fri, 09 Oct 2026 19:26:29 GMTModelshttps://system-one-models.com/entry/openai-decisions-api/https://system-one-models.com/entry/openai-decisions-api/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.Fri, 09 Oct 2026 19:26:29 GMTModelshttps://system-one-models.com/entry/bandits/https://system-one-models.com/entry/bandits/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.Thu, 08 Oct 2026 17:42:20 GMTToolshttps://system-one-models.com/entry/rejev/https://system-one-models.com/entry/rejev/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.Thu, 08 Oct 2026 17:40:59 GMTOpen Implementations