Laya benchmarks

The official Laya README publishes detailed numbers, and a growing set of independent repositories now test those claims. The overall picture: Laya is much faster when run locally and free to self-host, while Jev is more accurate out of the box on most shared tests.

228 projects

jev-arena

Samge0

Compares Jev, NanoJev, and Laya decisions in Tetris and 1024 with recorded gameplay replays

0·GitHub repo

computer-use-testing

yoaugust

Tests Jev, Laya, and CUA for computer-use tasks and plans further reinforcement-learning fine-tuning

0·GitHub repo

laya

DarkWanderer

Runs experiments with the open-source Laya System-1 decision model

0·GitHub repo

jev-laya

wuzhiping

Probes the multilingual Laya model on Apple Silicon and records machine-readable inference results

0·GitHub repo

laya-demo

tjpajala

Benchmarks Laya and Open-Jev on JevBench and PubMedQA with a Dockerized comparison interface

0·GitHub repo

laya-ft

Alexander-Ollman

A reproducible study benchmarks Jev against fine-tuned Laya on workflows and chat moderation

0·GitHub repo

laya-doom

cohenom

Displays Laya's live tactical votes alongside heuristic-driven Doom combat

0·GitHub repo

laya-chess

buzzo123

Provides chess games against a computer that selects moves using Laya

0·GitHub repo

Laya-test

LouisMoretti

Runs Laya locally for message classification and benchmarks its server and prediction performance

0·GitHub repo

laya-mlx

MohammadAsadi-7

Runs Laya typed-decision models natively on Apple Silicon using MLX

0·GitHub repo

laya-demo

cyyeh

Provides a Gradio playground, CLI scenarios, and device benchmarks for Laya

0·GitHub repo

laya-test

petrixh

Runs Laya as the decision-making pilot in a browser game with reproducible evaluations

0·GitHub repo

Laya-2048

DjTaNg-404

Uses local Laya weights to play 2048 with browser, terminal, and batch-testing interfaces

0·GitHub repo

laya-snake-cuda

kuchris

Compares Laya and SemIf for local real-time Snake decisions with a CUDA dashboard

0·GitHub repo

lunar-mpc-laya

mraad

Pairs Laya with adaptive model-predictive control in a lunar lander decision game

0·GitHub repo

laya-mlx-demo

knishika62

Uses laya-mlx to classify Japanese virtual streamer personas and compare results with an LLM

0·GitHub repo

jev-vs-laya

mouadse

Benchmarks hosted Jev, Kev-9B, and Laya on Moroccan Darija sentiment classification

0·GitHub repo

laya-onnx-runtime

zenryokukikai

Ports the Laya multilingual decision model to CPU-only ONNX Runtime

0·GitHub repo

laya-snake-arena

sathwikkuncham

Compares local Laya and Jev decision engines in a configurable Snake arena

0·GitHub repo

jev-laya-chess-bench

abe17124

Compares TypeSafe Jev and Laya in head-to-head chess games using legal moves

0·GitHub repo

jev-laya-japanese-business-benchmark

snsk

Compares Jev and Laya on a Japanese business decision benchmark

0·GitHub repo

decisionmakertest

vittoriobrehautduran

Benchmarks Jev and Laya on typed decisions, labeled cases, and a small dungeon game

0·GitHub repo

ai-decision-lab

uibuckets

Provides a local playground and benchmark harness for Laya, with optional Jev comparisons

0·GitHub repo

IOCArena

hc-nolan

Compares Jev, Von, and Laya decision models on VirusTotal data

0·GitHub repo

Official numbers

The core README and its BENCHMARKS.md report latency on a Tesla T4 (32.8 ms for one question with laya-multilingual, 39.5 ms with laya) and accuracy across 51 languages. Its Jev figures are third-party published, not measured by the Laya authors.

Independent head-to-heads

  • sysone-bench: byte-identical inputs across 751 states. Jev leads on triage, guardrails, moderation, Banking77 and multilingual intent. Laya leads on AG News and MNLI.
  • jev-laya-benchmark: 1,470 synthetic items. Jev 92.9% vs Laya 65.3% of judgments correct. For a single question, Laya was 42 ms locally on an M3 Pro and Jev was 136 ms. Jev was faster above 3 to 4 questions per request.
  • laya-jev-lab: 40 Chinese support tickets. Jev 78% at 588 ms, Laya 57% at 7.6 ms on an M4 Max. A cascade that escalates below 0.60 confidence matched Jev's accuracy at 1.8x its speed.
  • JevBench: a composite board. In v1.4.2, Laya (English, CPU) ranks 41st with a score of 30.25 and Jev 1.13.0 ranks 2nd with 63.29.
  • laya-mcp eval: key accuracy 32.5% for Laya vs 98.8% for Jev, with median latency of 26 ms vs 138 ms.

CPU latency

laya-cpu-benchmark measured laya-multilingual in steady state on an Intel i9-14900HX. One question took 50 ms for a 71-token state, 307 ms for 261 tokens, and 1,315 ms for 927 tokens. Batching gave little gain on CPU. Its conclusion: a realistic CPU call is 0.3 to 2 seconds, not 33 ms.

Run your own

git clone https://github.com/glukicov/laya_router && cd laya_router
uv sync --all-extras
uv run laya-router eval run --backend laya --device mps

Or use jevbench (dhruvmehra) to compare Jev, Laya, LLMs and BERT models on public datasets.

Reading these numbers

Most of these suites are small (40 to 1,500 items), synthetic or in one domain, and their authors say so. Latency depends on hardware, state length and question count. The core README's own advice: treat Laya as a fast base to specialise, and fine-tune for accuracy.

More ways to use Laya