LanguageEN简中

ModelDial · Integrations

API & Skill

Use ModelDial results in your own tools. Install the Skill for an AI assistant, or read the published data through the API.

Install the SkillRead the API
Agent SkillREST API

Install the Skill

Send the prompt below to a tool that supports Agent Skills, or install from the terminal. The Skill reads public results and requires no account or API key.

Install prompt
Install the ModelDial Skill from https://modeldial.com/modeldial-skill/SKILL.md. Review the linked files before writing to the skills directory.
Install from the terminal
Manual install for Codex, Gemini CLI, Copilot, or OpenCode
bash <(curl -fsSL https://modeldial.com/modeldial-skill/install.sh) --target agents

  1. Install into the directory your agent already uses

    The installer checks the files and updates an existing ModelDial Skill if needed.

  2. Start a new conversation

    Most tools discover Skills when a session starts. Reopen the tool or begin a fresh task after installation.

Verify with one question

Compare the published results for GPT-6.1 Sol and GPT-6 Sol, including their effort levels, axis scores, evaluation time and reference cost. Include source links and identify missing data.

The answer should includeThe model and effort level, test date or batch, supporting scores, and links to the ModelDial results.

If the data cannot be readThe Skill instructs the agent to report the failure instead of answering from older results or memory.

Agent SkillREST API

Data endpoints

Use compact JSON for current rankings. For audits, choose the Backend & Testing index or the three-capability publication index.

  • GET / JSON

    Current compact ranking

    /api/v1/radar/latest.json

    Default overall order with all three axis scores and weights, plus the compatible backend ranking.

  • GET / JSON

    Agent configuration profiles

    /api/v1/radar/agent-profile.json

    Balanced, quality, and value role assignments from published decision tags; not a paired-agent benchmark.

  • GET / JSON

    Latest comparable changes

    /api/v1/radar/changes.json

    Backend rank, score, time, and recommendation changes after a protocol compatibility check; cost deltas appear only when the pricing snapshot matches.

  • GET / JSON

    Backend & Testing publication index

    /api/v1/radar/index.json

    Backend batch identity, publication time, protocol fields, hashes, and complete snapshot links.

  • GET / JSON

    Capability publication index

    /data/benchmark-snapshots/index.json

    Latest verified batch identity and archive link for each capability and the weighted overall ranking.

  • GET / JSON

    Complete Backend & Testing snapshot

    /data/reference-snapshots/latest.json

    Question-level Backend & Testing results and provenance fields for audit work.

Current results

Example from current results

Checking latest

Published after verification

Example questions and interpretation limits

Ask for the decision you need

Ask about a new model, its predecessor or tested efforts. The Skill retrieves published scores and sources; historical backend changes are available separately when comparable records exist.

  • 01
    Current ranking
    Which configuration leads the current Radar, and why?
  • 02
    New model vs predecessor
    How do GPT-6.1 Sol and its predecessor GPT-6 Sol compare at their published efforts?
  • 03
    Your configuration
    I use GPT-6.1 Sol XHigh through the official login. Which alternatives have similar scores and shorter evaluation times?
  • 04
    Agent configuration
    How should I configure my main and worker agents from the latest ModelDial results? Start with the balanced profile, then show quality and value alternatives.

Answer rules and data sources

The Skill instructs the assistant to cite published results and identify missing data. Check the sources in its answer.

  1. Separate score differences from historical trends

    Current model comparisons use published scores. Historical backend movement requires matching protocols and is not an overall-ranking trend.

  2. Start from your configuration

    If the model, effort, or route is missing, the Agent asks before turning the top row into personal advice.

  3. Treat a drop as a signal

    One lower comparable score can justify another check, but not a claim that a provider changed the model.

  4. Keep acceptance with the main agent

    The worker gets bounded execution. Requirements, integration, and final acceptance stay with the main agent.

What the Skill will not claim

Use the published ranking

Publisher order is the ranking. The Skill does not rebuild it from score or provider names.

Separate score changes from their causes

A lower comparable score is a signal, not proof that a provider changed or degraded a model.

Confirm your settings

Without your exact configuration, the Skill reports the field or asks one short follow-up question.

Distinguish estimates from charges

Reference cost describes the controlled batch, not your invoice or actual usage charge.

Explain how role suggestions were derived

Role profiles use configurations evaluated independently across the latest published axis results, not a paired-agent benchmark.

Licensing and attribution

Skill instructions use the MIT License. Published Radar data uses CC BY 4.0 and should identify ModelDial and the source batch when practical.

Data licenseEvaluation methodSHA-256