DANE / README.md
bharathkoneti's picture
Model card v2: structure, metadata (model-index), tags, usage example, live links
c0a6388 verified
|
Raw History Blame
2.85 kB
metadata
license: other
license_name: inferock-terms
pipeline_tag: text-generation
inference: false
language:
  - en
tags:
  - hybrid-model
  - frontier
  - inferock
  - dane
  - chat
  - conversational
  - api
  - text-generation
  - hle
  - humanitys-last-exam
model-index:
  - name: Dane
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: Humanity's Last Exam (Diamond)
          type: cais/hle-diamond
        metrics:
          - type: accuracy
            name: >-
              HLE Diamond (with tools; graded as the Artificial Analysis board
              grades)
            value: 79.4
            verified: false
        source:
          name: Inferock
          url: https://inferock.ai

DANE: Decision Aware Neural Engine

Dane is a hybrid, frontier class model. It beats the frontier and delivers the most reliable answer on every request.

Model Details

Developed by Inferock
Model type Hybrid, frontier class model
Language English
License Inferock terms
Access API only, no weights on the Hub
Model id dane

What Dane is

Dane is a hybrid model made by Inferock. Dane scores 79.4 on HLE Diamond, 15 percent above the Artificial Analysis board leader. Dane is API-only: you reach it through the Inferock API as the model id dane, and no weights are published on the Hub.

Results

HLE Diamond: Dane 79.4, index leader 69.1

Benchmark Score
HLE Diamond 79.4
Artificial Analysis board leader 69.1

HLE Diamond is the 1,000-question Diamond set of Humanity's Last Exam (dataset cais/hle-diamond), run with tools and graded as the Artificial Analysis board grades: the official HLE judge prompt, GPT-5.6 Luna (medium) as the judge, pass@1. Score is right over judged: 794 of 1,000; a question with no answer counts as wrong. Run by Inferock, October 30 to November 4, 2026.

How to use

Dane answers a standard chat completions request with the model id dane. Sign up at https://inferock.ai, activate Serve, create a key, and use the base URL from your account.

curl https://<your-inferock-base-url>/v1/chat/completions \
  -H "Authorization: Bearer $INFEROCK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"dane","messages":[{"role":"user","content":"..."}]}'

Pricing

Pricing: 8 USD per million input tokens, 30 USD per million output tokens (billed tokens). Context window and modalities: as listed on https://inferock.ai/models/.

FAQ

How does Dane do it? Dane is built on one rule: a model's answer is a prediction, not a verdict. Everything else is how we measure it, and the results are on the releases page.

Links