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-lab

Parswanadh

Coordinates long-context decision-engine research for the open Laya model

0·GitHub repo

laya-indic-bench

jay123anta

Evaluates Laya decision models on Hindi and Assamese

0·GitHub repo

jev-laya-tetris

HarryReidx

Benchmarks TypeSafe Jev against local Laya in a competitive Tetris duel

0·GitHub repo

jev-n-laya

jcezardasilva

Compares Jev, Laya, Von, and Gemma on typed-decision tasks

0·GitHub repo

laya-lk-bench

mithilyr

Stress-tests Laya decision-model performance on Sinhala and Tamil offensive-language data

0·GitHub repo

laya-vs-jev

alilibx

Benchmarks open-weight Laya models against TypeSafe Jev on labelled datasets

0·GitHub repo

laya-cuda-bench

bhushankinge

Benchmarks Laya inference throughput, latency and cost across NVIDIA GPUs and serving backends

0·GitHub repo

laya-cn-study

Adkid-Zephyr

Collects Chinese-first post-training experiments, datasets, and evaluations for Laya

0·GitHub repo

laya-vs-jev-traffic

ameeetgaikwad

Compares local Laya and cloud Jev in a real-time traffic-control simulation

0·GitHub repo

jev-laya-classification-bench

bhushankinge

Benchmarks Jev, Laya, and Qwen on classification of federal IT solicitations

0·GitHub repo

von-laya-jev-paint-compare

zhangyunting123

Creates side-by-side paintings from typed decisions by VON, Laya, and Jev

0·GitHub repo

laya-coreml-vs-jev-benchmark

sallout

Compares Laya and Jev on zero-shot intent classification benchmarks

0·GitHub repo

laya-v2-agent-routing

mdad-elec

Fine-tunes a Laya System-One router to select the price tier for each agent turn

0·GitHub repo

cbjev

tomek7667

Implements a Jev-compatible decision model and benchmarks it directly against Laya

0·GitHub repo

korean-decision-benchmark

jkf87

Benchmarks SemIf, Decider, Laya, and Jev on Korean hate-speech classification

0·GitHub repo

synthetic-ehr-decision-evals

MadCodeTX

Benchmarks decision models on synthetic EHR administrative-routing tasks

0·GitHub repo

rlcd_x_1b-4b_instruct

mrgonzales-dev

Tests RLCD models including Laya and explores their use with 2B–4B models

0·GitHub repo

gyra

Gowtham-R-2002

Fine-tunes Laya for fast coding-agent decisions and evaluates it against labeled tests

0·GitHub repo

jev-vs-llms

ivanviragine

Compares Jev, Laya, other open models, and chat LLMs on loaded questions in two languages

0·GitHub repo

wizden-moonlander

WizdenOrg

A lunar lander game compares Laya and Jev as typed-decision flight controllers

0·GitHub repo

small-decision-model-cross-domain-degradation

SnackTerminator

A controlled study evaluates cross-domain and cross-lingual transfer in Jev-class decision models

0·GitHub repo

decision-models-under-pressure

gazelle93

A benchmark compares seven decision models as candidate lists grow, options reorder and distractors become harder

0·GitHub repo

ai-experiments

nadeem4

A collection of documented AI experiments reports protocols and results for model evaluations

0·GitHub repo

laya-playground

shwetankg07

Three browser games measure Laya’s decisions against exact ground truth

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