Google launches Gemini Decision 1 for batch closed-ended scoring
The Decisions API scores up to 1,000 questions in one pass and returns probabilities in 150 to 250 milliseconds.
Stories per day · 30 days
2 RSS
Relatedjev4benchmarks3calibration3typesafe3gemini2language-models2multimodal2on-policy-distillation2openai2rag2retrieval2typesafe-ai2agent-cost1agents1agent-security1ai-hype1ai-soc1alert-triage1
48 stories, newest first · one card per story
Stories tagged #decision-models
Hugging Face blog post covers decision models
No article body was available, so models, features, and availability cannot be determined.
MMDM benchmark tests 28 models on 5,448 decision tasks
Best hard multi-select accuracy is 36.81%; Decider-V1.2 falls from 78.75% on world knowledge to 47.95% on constraint planning.
Drex Open Decision Models Achieve State of the Art
Drex family of decision models including 8B to 35B parameters sets new benchmarks in accuracy and speed over autoregressive LLMs.
Flide accelerates decision inference with exact state forking
Flide decouples logical tree structure from execution in a flattened token stream using ForkAttention, achieving up to 9.5x speedup over vLLM while preserving exact probabilities.
DecisionRank on-policy distillation beats generative teacher on retrieval tasks
Item-space OPD lets 1.7B DecisionRank surpass 27B LLM teacher on TREC DL while running 24.5x faster.
Flide answers decision queries up to 9.5 times faster than vLLM
ForkAttention keeps each query branch identical to an isolated forward pass while reusing GPU-resident graphs and checkpoints.
DecisionRank trains decision model rerankers
DecisionRank achieves SOTA on TREC DL and BEIR with a 1.7B model that surpasses its 27B generative teacher.
Hugging Face introduces AnySpeechRecognizer and AnyDecisionModel
The announcement covers open models for speech recognition and decisions on Apple platforms, with no further details available.
DecisionUnlearn-Bench measures unlearning when decision schemas change
On BANKING77, full-to-oracle displacement rose from example deletion to class deletion across 20 configurations.
Decision models type RAG source conflicts cheaper than Gemini
Eleven decision models hit 50.0–67.0% on CONFLICTS, and 10 matched or beat Gemini 2.5 Flash at 4–39x lower billed cost.
Decision models classify conflicts in RAG sources
Typed decision models classify knowledge conflicts in RAG faster and cheaper than LLMs while preserving response behavior.
Author says TypeSafe AI’s Jev hype has already collapsed
The note calls Jev a cheap classifier that can still be wrong, and says open-weight rivals beat it on cost.
1
OpenAI widely releases Decisions API amid Jev model race
Handa says latency fell to about 100–180 ms, while public indexes still rank dedicated models higher.
Paper tests which rule and input changes drive decision-model answers
Controlled arithmetic-rule tests separate transfer from joint reliability and show wording and table edits change answers.
DecisionPivot benchmark separates decision accuracy from confidence
Two 27B models only 2.6 points apart on the reference track score 70.1% and 44.2% on contrast groups.
20 Jev Alternatives: The Decision Models Taking On TypeSafe in 2026
MarkTechPost lists 20 decision-model alternatives it says are challenging TypeSafe in 2026.
9
Jev 1.13 raises agent cost 19% without improving pass rate
On 21 held-out Terminal-Bench 2.1 tasks, Jev matched a 73.0% pass rate but cost 22% more than a placebo.
TUPLE-Bench finds typed decision outputs leak withheld causes
Across nine models, 91.88% to 99.93% of responses revealed a withheld cause through selection or scores.
AI Decision Models and Their Impact on AI SOC Platforms
Decision models from TypeSafe, OpenAI, and Cribl offer scored answers aimed at SOC alert triage.
8
Jev and other decision models can still be tricked with prompt injection
HiddenLayer shows TypeSafe AI's Jev decision model can still be steered by indirect prompt injection.
6
Intern-Decision: Efficient Multimodal Decision Making with Autoregressive Masked Language Modeling
Intern-Decision's 4B model hits 90.02% decision accuracy with 44 ms latency on an RTX 4090.
LEV deepens decision models by looping layers instead of tokens
A 2.6B LEV rose from 63.2% to 76.2% on JevBench between depth one and depth four.
StartLux-Decision: AutoThink Decision Models with Reinforcement Learning for Calibrated Deliberative Decisions
StartLux-Decision models from 0.8B to 27B add confidence-guided reasoning trained with RLCD².