Benchmarks and comparisons with decision models

Live race labelling 1,000 app reviews with four typed Jev questions versus Gemini 3.8 Flash JSON output.

Jev plays Chrome Dino and a local shooter arena from structured state, with speculative jump/duck questions and code-owned execution.

Flappy Arena races Jev against GPT-6 Luna on the same seeded Flappy Bird course, each choosing flap or wait live.

Classifies 1,000 arXiv AI papers into 24 topics with one Jev Choice each and checks agreement against an LLM judge.

Jev-protocol-compatible random baseline server in Rust: answers noul, choice and score with fast pseudo-random numbers, as a mock or floor.

Web Snake autoplay where each move is a System One Choice from Jev or wire-compatible Drex, with a side-by-side compare mode.

Browser table tennis against Jev, where every paddle position is a live Choice among pixel-labelled bands with no local prediction.

Trade Arena proof of concept comparing trading strategies on 13 US stock funds, grown out of a pre-registered Jev study.

Browser arena where local Laya and hosted Jev race in Snake and fight in a Mortal-Kombat-style game, with every move a real decision.

Chrome T-Rex game where local Laya on MLX and hosted Jev choose moves side by side, with latency charts and crash replays.

Experimental Conway's Life game where Jev makes each move with one boolean per legal cell, plus a broker that wraps any LLM as Jev.

Jev-compatible open System One engine with a Claude Code-style terminal REPL showing live probabilities, plus an experiment harness.

Browser Pac-Man race comparing hosted Jev and self-hosted Laya choosing routes from the same board state, after code removes fatal routes.

Novelty demo that turns Jev answers to 22 Boolean gate questions into lookup tables for a simulated RISC-V CPU running compiled C.

Hackathon arena where 200 people attack a support agent and a Jev allow/block/escalate gate on every tool call is hardened each round.

Browser arcade games (2048, runner, chess, Flappy Bird, Sudoku) where small decision models choose each move from text options.

Browser lane-racing demo where Jev, OpenAI Decisions and a local EmbeddingGemma model each choose a lane for the same obstacles.

Portuguese workshop: a LangGraph sales agent where each decision step can be made by Jev or a frontier LLM and measured side by side.

Benchmark testing whether Jev or open Kev can replace an LLM judge in agent guardrail callbacks on 7,925 public examples.

33-chapter Chinese tutorial on agentic RL and GRPO, including a chapter on when Jev-style external decision models beat training with RL.

Study of Jev's choices in multi-armed bandits, testing whether Bayesian instructions and supplied statistics improve its exploration.

Experiments testing whether Jev can spot positive-expected-value dice bets from payout tables, and whether recent wins or losses sway it.

Deterministic evidence selector for noisy Codex investigations; its earlier Jev subagent router is kept for the record, not recommended.

Pre-registered field test of Jev, GLiNER2.5-Decide, Laya and other decision models against small LLMs on fresh September 2026 data.

Experiment using Jev Noul judgments on accumulated evidence to decide when Zilliz's DeepSearcher agent should stop searching.

GoodWatch movie and TV recommendation monorepo, listed for an experiment comparing Jev question designs for attribute scoring.

Bilingual research report on what Jev is, how its claims compare with independent evidence, and the open-source alternatives.

Zero-shot run of Jev 1.13 on all seven LexGLUE legal tasks (23,607 examples) versus GPT-5.6 Luna, open models and fine-tuned BERT.

Six recorded chess experiments with Jev via OpenRouter, candidly showing that unaided Jev still blunders pieces.

Pre-specified study running Jev and GPT-4.1 as 300 synthetic survey respondents; question format mattered more than model.