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-mlx

mizorewww

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

6.3k·GitHub repo

laya-coreml

mizorewww

Runs Laya typed-decision models locally on Apple Silicon using Core ML and the Neural Engine

1.4k·GitHub repo

openJev-verdict-2.0

Heman10x-NGU

Develops and benchmarks a non-autoregressive typed-decision model against Jev and Laya

285·GitHub repo

laya-playground

wdobry

A local website combines Laya model demos, games, a benchmark, and an agent skill

157·GitHub repo

laya-vs-jev

virajbhartiya

A side-by-side T-Rex game compares local Laya and hosted Jev decision models

100·GitHub repo

laya-mps

afshinm

Runs Laya typed-decision inference locally on Apple Silicon using Metal Performance Shaders

21·GitHub repo

lev

jlt-commons

Implements a typed decision engine using Laya checkpoints and GGUF chat models

17·GitHub repo

edgejev

yzfly

Exports, quantizes, and serves Laya and other Jev-style models for offline CPU inference

11·GitHub repo

laya-jev-lab

yibie

Compares Jev and Laya decision models and evaluates a local-first inference cascade

9·GitHub repo

laya_router

glukicov

A Python model router compares local Laya decisions with a GPT-5 nano routing model

6·GitHub repo

jevbench

dhruvmehra

A reproducible benchmark compares JEV, Laya, and other classifiers across datasets and metrics

6·GitHub repo

laya-onnx

MstyAI

Runs Laya decision models locally with ONNX Runtime through a Go library and CLI

5·GitHub repo

laya-plays-smb3

cv

Demonstrates Laya controlling Super Mario Bros. 3 with recorded, replay-verified decisions

5·GitHub repo

reflexbench

brida-ai

Benchmarks Laya and other typed-decision engines across quality, calibration, robustness, and latency

5·GitHub repo
L

laya-jev-benchmark

Luni

Benchmarks Laya against Jev and other models on phishing detection and calibration

4·HF dataset
C

MacJev-322M-4K-Laya

chaoliangUNSW

Fine-tunes Laya for long-context local Mac agents and compares it with the base model

4·HF model

jev-laya-benchmark

harrymunro

Benchmarks local MLX Laya against TypeSafe's hosted Jev on synthetic decision tasks

4·GitHub repo

sysone-bench

instax-dutta

Compares Laya and Jev on identical inputs across multiple decision benchmarks

4·GitHub repo

jev-tests

schacon

Compares Laya, Jev, Kev, and Claude in three macOS typed-decision demos

4·GitHub repo

chunklaya

myxamediyar

Chunks long documents and uses Laya for typed-decision lookup across inputs up to one million tokens

3·GitHub repo

zero-shot-ie-bench

umstek

Compares Laya and other zero-shot systems across information-extraction and classification tasks

3·GitHub repo

structured-decision-bench

zhengbangbo

Benchmarks structured decisions from Qwen3, Jev, and Laya CoreML

3·GitHub repo

runtime-tutorials

Runtime-weekly

Provides runnable Python guides for Laya classification and a comparison of Laya with other systems

3·GitHub repo

doomLaya

azalio

Trains and compares Laya and Jev agents playing FreeDoom with reproducible results

3·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