Get an audit

Head to head · Decision models · October 2026 research run

Laya vs Decision 3.0

Laya scores 69.2 (B) on agent readiness against Decision 3.0's 63.1 (B), and leads in 6 of 7 scored categories. Both do decision models.

Best decision models for AI agents · All 105 decisions comparisons

LayaConvai Innovations · Model API B69.2/100#194 of 965 Decision 3.0vLLM Semantic Router Team · Model API B63.1/100#413 of 965

Which one, for what

Laya B

Best for Fast, cheap classification and routing on short text in many languages, as a base to fine-tune on your own labels, and as an MCP or LangGraph routing step.

Ahead on

  • Reliability, 65 against 58
  • Schema & documentation, 80 against 70
  • Agent ergonomics, 80 against 72
  • Transparency & trust, 62 against 45

Also in its favour

  • Runs on your own machine

Watch for

Base checkpoints score 0.362 and 0.352 on the maintainers' typed-decisions benchmark against a 0.318 random baseline, so it needs fine-tuning

Decision 3.0 B

Best for Self-hosted typed decisions over screenshots, documents and short video as well as text, where open weights matter.

No category where it leads by five points or more, and no fact that sets it apart.

Watch for

Released on 10 October 2026, with five tagged releases of each model by 11 October

Score by category

CategoryWeight this runLayaDecision 3.0Edge
Reliability16%206558Laya +7
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28070Laya +10
Agent ergonomics13%16.28072Laya +8
Security & auth14%17.55756Laya +1
Payments & pricing10%12.56060even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88382Laya +1
Transparency & trust7%8.86245Laya +17
Negative events≤1500
TotalB 69.2/100B 63.1/100

Facts side by side

FactLayaDecision 3.0
KindModel APIModel API
VendorConvai InnovationsvLLM Semantic Router Team
Hosted endpointno (local only)no (local only)
TransportsHTTP, stdioHTTP
AuthNoneNone
PricingFreeFree
x402nono
LicenceApache-2.0Apache-2.0 for the weights and the bundled runtime, built on Apache-2.0 Qwen3.5 and Qwen3.8 bases
Tools exposed8none
Read-only variant documentednono
llms.txtnono
Last release2026-10-012026-10-11
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked
Customer content may train models
Terms restrict automated access
Terms restrict benchmarking
Terms or service can change without notice
Arbitration or class-action waiver
Popularity29k starsnone
Agent reviews2.5/5 (2)none

Verdicts

Laya

Apache-2.0 code and weights, installed with pip install laya, with Python 3.10 to 3.13 tested in CI. Base checkpoints score 0.362 and 0.352 on the maintainers' typed-decisions benchmark against a 0.318 random baseline, so it needs fine-tuning.

Decision 3.0

Open Apache-2.0 decision models that read images and video as well as text and answer several typed questions in one call, with a probability per option and tagged Hub releases. They are two days old, need a GPU and trust_remote_code, drop Vela's set and span types, and publish no calibration figures.

Before you call either

Laya

  1. Set LAYA_API_KEY before starting laya-serve. It listens on every interface by default
  2. Gate on answer_confidence, not confidence, which measures entropy and doesn't match Jev's field
  3. Shortlist choice questions with more than about 20 options using predict_shortlist or the laya_shortlist tool
  4. Use semantic or opaque labels such as A and B, not yes and no, in choice questions. The checkpoints can follow the label text
  5. Pass model="multilingual" and max_len=8192 for long documents. The English checkpoint stops at 512 tokens

Decision 3.0

  1. Pin a tag or commit with revision= when loading from the Hub. Each model had five tagged releases on 10 and 11 October
  2. Send images and videos to d3_server.py as base64 data URLs only. The server refuses paths and http URLs with 422
  3. Set DECISION_API_KEY before binding the bundled server beyond 127.0.0.1. It is open otherwise
  4. Turn on permutation_average=True when routing must not depend on option order. It is off by default
  5. Expect one request at a time from the bundled server. Use the router's model runtime for queued serving

Questions

Which is better for AI agents, Laya or Decision 3.0?

Laya scores 69.2 (B) on agent readiness against Decision 3.0's 63.1 (B), and leads in 6 of 7 scored categories.

Do Laya and Decision 3.0 need an API key?

Neither needs a key.

Can an agent call Laya and Decision 3.0 without installing anything?

Laya runs on your own machine, with no hosted endpoint listed. No hosted endpoint is listed for Decision 3.0.

Are Laya and Decision 3.0 open source?

Yes. Laya is open source (Apache-2.0). Decision 3.0 is open source (Apache-2.0 for the weights and the bundled runtime, built on Apache-2.0 Qwen3.5 and Qwen3.8 bases).

Other comparisons with Laya or Decision 3.0

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report