ENPT

Dinah-1

Last updated:

Open21–76ms$0/M input

Quadrant scores

See the full quadrant

Scored with the public quadrant rubric (maturity × capability; bubble = adoption). Revise as evidence lands.

  • Maturity5/10

    Apache-2.0 150M encoder with ONNX files (int8 and 8-bit) and inference code that runs on a CPU, in English and Portuguese, 8,192-token context. Ships tool, code and calculator experts. Independent author, no hosted API, no SLA.

  • Capability5.9/10

    Decision Index 0.4.1 (22 Oct) Full 16.36 (#193), far below Jev 1.13 (59.22). Choice, noul and score with probabilities and a confidence; temperature per question type, no ECE. Median 20.8 ms, p95 76.4 ms in the official run on a shared GPU.

  • Adoption1/100

    About 23 downloads and one like (20 Oct). No integrations or production users found.

Vendor claims

publicado (OK do Fabricio 20/10 BRT). Scores are calculated from scratch.

What it is

150M Apache-2.0 encoder for typed decisions in English and Portuguese on a CPU, with tool and calculator experts. Decision Index 0.4 Full 16.08 (#172). Source: huggingface.co/Lukitaduarte/dinah-1. Continues Dinah-0 Apache with the same architecture and question format.

Board result

Board Row Result
Decision Index 0.4 (20 Oct 2026) Dinah-1 Full 16.08 (#172); Jev 1.13 61.26 (#34), Jev 1.14 62.22 (#28)

Not checked against JevBench or Artificial Analysis for this page; the boards are never combined.

Vendor claims (UnverifiedClaim)

  • Decision Index 0.3 public index 34.32 (official kit run), against 25.86 for Dinah-0 Apache (source)
  • Latency in the official run on a shared GPU: median 20.8 ms, p95 76.4 ms, mean 41.3 ms (source)

Scores (from scratch, 20 Oct 2026)

  • Capability 5.9 = types × 0.30 + calibration × 0.25 + latency × 0.25 + accuracy × 0.20 = 10 × 0.30 + 4 × 0.25 + 6 × 0.25 + 2 × 0.20 = 5.90. Accuracy: 8 × 16.08 ÷ 61.26 = 2.10 → 2.
  • Maturity 5.0 = availability × 0.30 + docs × 0.25 + integrations × 0.25 + support × 0.20 = 7 × 0.30 + 7 × 0.25 + 3 × 0.25 + 2 × 0.20 = 5.00.
  • Adoption 1 = engagement × 0.35 + ecosystem × 0.35 + production × 0.30 = 1 × 0.35 + 1 × 0.35 + 0 × 0.30 = 0.70 → 1.

Board audit (22 Oct 2026, DI 0.4.1)

publicado (OK do Fabricio 22/10 BRT).

Decision Index 0.4.1 (22 Oct; reference Jev 1.13 Full 59.22, was 61.26 on 0.4) lists this page’s row at Full 16.36 (#193). Accuracy rule: 8 × 16.36 ÷ 59.22 = 2.21 → 2 (was 2). Capability unchanged. Maturity and adoption unchanged.