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

Laya-Showcase

zamax14

Demonstrates and benchmarks multilingual Laya alongside Jev and GPT models

3·GitHub repo

decision-systems-bakeoff

actuallyrizzn

Runs a reproducible benchmark comparing Flybrain, Jev, and Laya on four public tests

3·GitHub repo

flappy-laya-openvino-cpu

rupeshs

Runs Laya inference with OpenVINO to control a Flappy Bird game on CPU

3·GitHub repo
W

laya-multilingual-FP8

Weidows

Provides an FP8 per-row quantization of the multilingual Laya checkpoint with multilingual evaluation results

2·HF model

LayaSnakeGame

AmirTahaMim

A Pygame Snake game compares human play, a greedy baseline, and local Laya decisions

2·GitHub repo

laya-snake

zxrneu

Builds an autonomous Snake game agent using Laya decisions and BFS pathfinding

2·GitHub repo

JevCoreML

GodModeAI2025

Provides Core ML decision models, a Swift package, an HTTP server, and a demo app

2·GitHub repo

laya-as-judge

rbrus

Uses Laya-MLX to evaluate models and agents with typed-decision judgments

2·GitHub repo

laya-vs-jev

zaferayan

Benchmarks multilingual Laya against hosted Jev across 900 cases, three tasks, and six languages

2·GitHub repo

stuntdouble

ReallyArtificial

Proxies Jev requests to local decision models and compares their answers on recorded traffic

2·GitHub repo

laya-cuda

Alexw1111

Provides a lightweight CUDA inference library for Laya

2·GitHub repo

laya-cpu-benchmark

taiheqi718-art

Measures steady-state CPU latency for the multilingual Laya model

2·GitHub repo

laya-ternary-lite

xixi3548942758-design

Quantizes Laya to ternary weights for smaller, lower-memory inference

2·GitHub repo

laya-thalamus

lcbkmm

Middleware uses Laya for agent tool routing with confidence-based LLM fallback and evaluation

2·GitHub repo
A

laya-typed-decisions

akshatbindal

Fine-tunes Laya on the typed-decisions benchmark and compares results with Jev

1·HF model
R

laya-ov-int8

rupeshs

An int8 OpenVINO export of Laya for CPU inference

1·HF model

decision-model-playground

tedliou

A local web playground comparing Laya and Jev for recommending articles

1·GitHub repo

laya-tetris-finetuning

hama-jp

Fine-tunes Laya for real-time Tetris placement decisions and documents the experiments

1·GitHub repo

jev-vs-open-decision-models

elcronos

Benchmarks Jev against Laya and PrismNLI on zero-shot text classification tasks

1·GitHub repo

sokudan

hiroki-abe-58

Builds a Japanese typed-decision model and benchmarks it against Laya

1·GitHub repo

laya

xosi

Runs Laya typed-decision inference locally on Apple Silicon with MLX

1·GitHub repo

jev-vs-laya

DDnim

Benchmarks Jev and Laya on typed decisions for reviewing SQL statements

1·GitHub repo

laya-jev-arena

dante01yoon

Compares local Laya and hosted Jev models in games and measurement tools

1·GitHub repo

chinese-workflow-decision-bench

Adkid-Zephyr

Benchmarks Jev and Laya on synthetic Feishu message classification scenarios

1·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