Benchmarks and comparisons with decision models

TypeLLM: Jev-inspired type-safe decoding for existing autoregressive LLMs on SGLang, with schema-guaranteed typed outputs.

Side-by-side tool comparing Jev and DeepSeek on labelling the same comments for relevance, sentiment and intent, with replay and reports.

Jev as a calibrated reranker: query plus up to 30 documents in one call, one relevance Noul per document, benchmarked on BEIR.

Browser-agent benchmark with five timed events from one prompt, plus a ~200-line DevTools agent where Jev picks each action.

Evaluation suite for decision models with 23,900 pinned rows across nine task families and three primitives, plus a leaderboard.

ego-decision-layer: measured, pluggable decision layer for ego lite where Jev picks operation and target in one request.

Fifteen live arcade games where Jev and LLMs play each other, led by WikiRace in which Jev picks only real links.

Plugs any CDP browser, including engines that never draw a page, into a Jev loop that picks operations and targets from the DOM.

MCP server exposing Jev as one evaluate tool, plus a harness comparing Jev's judgments with general LLMs on shared datasets.

On-call tooling where Jev judges alerts and incident hypotheses and plain code decides: alert routing plus a no-LLM root-cause benchmark.

Open-source BYOK arena where Jev faces another model as a judge on your question, with blind voting before costs are revealed.

pytest-style tool that pins fixtures and expected Jev answers, then fails a model upgrade when answers flip or confidence drops.

One-page web app where Jev plays chess against OpenRouter LLMs, Stockfish or you, showing the moves it weighed and their probabilities.

Python agent runtime where Jev Choice decisions pick tools and arguments, and low-confidence picks go to an LLM for review.

Pac-Man where Jev or other System One models choose each move at junctions, with live odds, fallbacks and a leaderboard.

Test harness for any Jev-API decision model: accuracy, calibration and robustness probes for reordering, injection and padding.

Docker recipes and ARM64 images for serving ten native decision checkpoints, such as Cloudflare Clef, behind /v1/systemone on DGX Spark.

PyTorch factor-research stack with 213 factors and cost-aware backtests, plus a preview typed portfolio-decision adapter.

Slack-like playground for watching computer-use agents work, with replays, comparable runs and Jev choosing from a menu of visible actions.

Zero-dependency Node proxy that shadows Jev with local decision models and reports whether you can safely swap, per question and policy.

Rust port of TypeSafe's system-one-adapter that answers System One questions with OpenAI or Anthropic LLMs for comparison with Jev.

Browser chess lab where Jev, LLMs and people play, each Jev turn being one Choice over the legal moves, with Stockfish analysis.

Browser automation where Jev picks every step from a sightmap's named actions and reports whether the goal is met.

Claude Code hook that, when you write an LLM call or classifier, injects a three-way test: plain code, frontier model or Jev.

Milvus-based multi-hop graph RAG library where two-stage Jev Noul scoring selects relations and reranks passages.

Local SvelteKit workbench and CLI for organizing, editing, running and comparing Jev experiments defined as JSON.

NiceGUI desktop chess app for evaluating Jev's move choices against Stockfish, random players or itself, with PGN export.

One-page playground and test bench for Jev with TypeSafe, OpenRouter, LLM-baseline and mock backends behind one /v1/systemone contract.

Browser 2D driving sim where Jev answers lane, speed, hazard and pedestrian-yield questions every 200 ms, with an LLM comparison mode.

Real-time versus Tetris where Jev and an LLM or open Laya model pick placements on the same seeded pieces and clock.