Is Deployxa LM 1.0 state of the art?Pending benchmarks.Announced Oct 20, 2026; no independent results yet.

The details so far

Lab

Deployxa

Announced

Oct 20, 2026

API

Not yet

Open weights

Published

Parameters

1.5B

Lab

Deployxa

Weights

Apache 2.0 LoRA adapter on Hugging Face (base Qwen2.5-Coder-1.5B-Instruct); Ollama deployxa/deployxa-lm

Footprint

860 MB (Q4_K_M GGUF)

Output

JSON remediation recipes; abstains and escalates on thin telemetry (lab statement)

Eval harness

Cloud SRE Bench on GitHub (26-case public subset), the lab's own; not Vals AI's SRE Bench

Hosted

Live console at chat.deployxa.com; powers Deployxa Cloud's orchestrator (lab statement)

Tags marked unsure are not stated on the lab's own pages.

What would let us call it

Verdicts use only independent boards we already track. Two consecutive snapshots are required before any crown.

• Publicly announced with a source
• Usable by the public (API or weights)
• Listed on an independent board we track
• Enough results for a rank in a category
• Holds across two snapshots (crowns only)

What the lab claims

Self-reported. Shown for context; not used in any verdict.

Lab claim: on its 384-incident eval, root-cause accuracy 76.4% (GPT-4o 71.4%, Claude 3.5 Sonnet 69.2%) and verified container recovery 48.2% (GPT-4o 37.3%).

Lab claim: 5.8% false alarms, 16× fewer than regex rules, and 0/50 prompt leaks.

Sources