Get an audit

Head to head · Decision models · October 2026 research run

Decision 3.0 vs GLiClass

Decision 3.0 scores 63.1 (B) on agent readiness against GLiClass's 49.9 (D), and leads in 5 of 7 scored categories. GLiClass leads on transparency & trust. Both do decision models.

Best decision models for AI agents · All 105 decisions comparisons

Decision 3.0vLLM Semantic Router Team · Model API B63.1/100#413 of 965 GLiClassKnowledgator · Model API D49.9/100#793 of 965

Which one, for what

Decision 3.0 B

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

Ahead on

  • Reliability, 58 against 43
  • Schema & documentation, 70 against 49
  • Agent ergonomics, 72 against 60
  • Security & auth, 56 against 38
  • Maintenance & community, 82 against 44

Watch for

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

GLiClass D

Best for Topic, intent and sentiment routing over a known label set on the owner's own CPU or GPU, where many labels must be scored at once.

Ahead on

  • Transparency & trust, 64 against 45

Watch for

No calibration evidence. The cards report F1 only, and the docs tell users to calibrate thresholds on their own traffic

Score by category

CategoryWeight this runDecision 3.0GLiClassEdge
Reliability16%205843Decision 3.0 +15
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.27049Decision 3.0 +21
Agent ergonomics13%16.27260Decision 3.0 +12
Security & auth14%17.55638Decision 3.0 +18
Payments & pricing10%12.56060even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88244Decision 3.0 +38
Transparency & trust7%8.84564GLiClass +19
Negative events≤1500
TotalB 63.1/100D 49.9/100

Facts side by side

FactDecision 3.0GLiClass
KindModel APIModel API
VendorvLLM Semantic Router TeamKnowledgator
Hosted endpointno (local only)no (local only)
TransportsHTTPHTTP
AuthNoneNone
PricingFreeFree
x402nono
LicenceApache-2.0 for the weights and the bundled runtime, built on Apache-2.0 Qwen3.5 and Qwen3.8 basesApache-2.0 (library and the model weights we checked)
Read-only variant documentednono
llms.txtnono
Last release2026-10-112026-07-21
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
Popularitynone555 stars, 13k PyPI/wk

Verdicts

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.

GLiClass

An Apache-2.0 classifier that scores a whole label set in one encoder pass on the owner's hardware, with single-label, multi-label, hierarchical and few-shot modes. It returns label scores with no calibration claim, the bundled server has no authentication, and the last three test runs on the main branch, on 24 September 2026, failed.

Before you call either

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

GLiClass

  1. Pass --host 127.0.0.1 to python -m gliclass.serve, or put the port behind your own gateway. The server checks no credential
  2. On a machine without a GPU add --device cpu --dtype float32 --num-gpus-per-replica 0. The default configuration expects CUDA
  3. Send one text a request to POST /gliclass. An array in texts is cut to its first item without an error
  4. Set multi_label to false for one label from a set. The default scores each label independently, so scores do not sum to 1
  5. Keep text plus labels under the pipeline's 1,024-token max_length, or use ZeroShotClassificationWithChunkingPipeline. Longer input is truncated silently

Questions

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

Decision 3.0 scores 63.1 (B) on agent readiness against GLiClass's 49.9 (D), and leads in 5 of 7 scored categories. GLiClass leads on transparency & trust.

Do Decision 3.0 and GLiClass need an API key?

Neither needs a key.

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

No hosted endpoint is listed for Decision 3.0. No hosted endpoint is listed for GLiClass.

Are Decision 3.0 and GLiClass open source?

Yes. 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). GLiClass is open source (Apache-2.0 (library and the model weights we checked)).

Other comparisons with Decision 3.0 or GLiClass

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