CodexMaster
Tuesday, July 21, 2026
SignalRankingsDigest
AllCodingCowork

Live · scoring v2 · no pay-for-placement

Rankings

Every tracked entity on one 0–100 market signal — Objective 40% · Sentiment 40% · Opinions 20%. Recomputed live from the pricing summary, the release log, the immutable vote log and the discussion extract; never read from a stored column. Expand any row to see exactly why it sits where it sits — the methodology is public.

AllCodingCowork28 entities
  1. 1
    GitHub CopilotGitHub / Microsoftcoding agentdata unverified

    IDE assistant and coding agent.

    No votes yet
    69.0/ 100 · provisional
    Why is GitHub Copilot #1?
    Objective (hard data)weight 40%39.0/40
    Sentiment (votes)weight 40%provisional — not enough data
    Opinions (discussion)

Ties break on the entity slug, ascending — a fixed, public, unpurchasable identity. No pay, featured or sponsorship signal exists in the data model, let alone in the ordering. Vote on any entity: better, same, or worse than yesterday.

The digest · weekly

Rankings move weekly. So should you.

Rank changes, repricings, and the releases behind them — one email a week.

A weekly, vendor-neutral digest of the coding-agent stack. Unsubscribe anytime.

CodexMaster
SignalRankingsDigestFull streamMethodologyThe Honest Stack

CodexMaster is independent and not affiliated with OpenAI, Anthropic, xAI, Google, or any tool it covers. No pay-for-placement — ever. Rankings are computed from public methodology; sponsors are labeled and never ranked.

© 2026 CodexMaster. All rights reserved.

weight 20%
provisional — not enough data

Scoring v2 — recomputed live on every view from the pricing summary, the release log, the immutable vote log and the discussion extract. Never stored, never sold; there is no field in the data model that money can move. Public methodology →

Full breakdown, cited events & pricing log →

  • 2
    Claude CodeAnthropiccoding agentdata unverified

    Terminal, mobile, and web agent from Anthropic.

    No votes yet
    63.8/ 100 · provisional
    Why is Claude Code #2?
    Objective (hard data)weight 40%34.7/40
    Sentiment (votes)weight 40%provisional — not enough data
    Opinions (discussion)weight 20%9.1/20

    Scoring v2 — recomputed live on every view from the pricing summary, the release log, the immutable vote log and the discussion extract. Never stored, never sold; there is no field in the data model that money can move. Public methodology →

    Full breakdown, cited events & pricing log →

  • 3
    OpenAI CodexOpenAIcoding agentdata unverified

    Codex web, CLI, and desktop agent from OpenAI.

    No votes yet
    63.2/ 100 · provisional
    Why is OpenAI Codex #3?
    Objective (hard data)weight 40%33.0/40
    Sentiment (votes)weight 40%provisional — not enough data
    Opinions (discussion)weight 20%10.2/20

    Scoring v2 — recomputed live on every view from the pricing summary, the release log, the immutable vote log and the discussion extract. Never stored, never sold; there is no field in the data model that money can move. Public methodology →

    Full breakdown, cited events & pricing log →

  • 4
    Gemini CLIGooglecoding agentdata unverified

    Google's terminal coding agent.

    No votes yet
    59.7/ 100 · provisional
    Why is Gemini CLI #4?
    Objective (hard data)weight 40%29.7/40
    Sentiment (votes)weight 40%provisional — not enough data
    Opinions (discussion)weight 20%provisional — not enough data

    Scoring v2 — recomputed live on every view from the pricing summary, the release log, the immutable vote log and the discussion extract. Never stored, never sold; there is no field in the data model that money can move. Public methodology →

    Full breakdown, cited events & pricing log →

  • 5
    Kimi CodeMoonshot AIcoding agentdata unverified

    Moonshot's coding agent.

    No votes yet
    57.2/ 100 · provisional
    Why is Kimi Code #5?
    Objective (hard data)weight 40%24.0/40
    Sentiment (votes)weight 40%provisional — not enough data
    Opinions (discussion)weight 20%13.2/20

    Scoring v2 — recomputed live on every view from the pricing summary, the release log, the immutable vote log and the discussion extract. Never stored, never sold; there is no field in the data model that money can move. Public methodology →

    Full breakdown, cited events & pricing log →

  • 6
    KiroAWScoding agentdata unverified

    Amazon's spec-driven agentic IDE.

    No votes yet
    56.0/ 100 · provisional
    Why is Kiro #6?
    Objective (hard data)weight 40%26.0/40
    Sentiment (votes)weight 40%provisional — not enough data
    Opinions (discussion)weight 20%provisional — not enough data

    Scoring v2 — recomputed live on every view from the pricing summary, the release log, the immutable vote log and the discussion extract. Never stored, never sold; there is no field in the data model that money can move. Public methodology →

    Full breakdown, cited events & pricing log →

  • 7
    WindsurfCognitioncoding agent

    Agentic editor (formerly Codeium).

    No votes yet
    54.7/ 100 · provisional
    Why is Windsurf #7?
    Objective (hard data)weight 40%24.7/40
    Sentiment (votes)weight 40%provisional — not enough data
    Opinions (discussion)weight 20%provisional — not enough data

    Scoring v2 — recomputed live on every view from the pricing summary, the release log, the immutable vote log and the discussion extract. Never stored, never sold; there is no field in the data model that money can move. Public methodology →

    Full breakdown, cited events & pricing log →

  • 8
    CursorAnyspherecoding agentdata unverified

    AI-first code editor.

    No votes yet
    54.3/ 100 · provisional
    Why is Cursor #8?
    Objective (hard data)weight 40%28.0/40
    Sentiment (votes)weight 40%provisional — not enough data
    Opinions (discussion)weight 20%6.3/20

    Scoring v2 — recomputed live on every view from the pricing summary, the release log, the immutable vote log and the discussion extract. Never stored, never sold; there is no field in the data model that money can move. Public methodology →

    Full breakdown, cited events & pricing log →

  • 9
    AntigravityGooglecoding agentdata unverified

    Google's agent-first IDE.

    No votes yet
    53.3/ 100 · provisional
    Why is Antigravity #9?
    Objective (hard data)weight 40%23.3/40
    Sentiment (votes)weight 40%provisional — not enough data
    Opinions (discussion)weight 20%provisional — not enough data

    Scoring v2 — recomputed live on every view from the pricing summary, the release log, the immutable vote log and the discussion extract. Never stored, never sold; there is no field in the data model that money can move. Public methodology →

    Full breakdown, cited events & pricing log →

  • 10
    DeepSeek V4DeepSeekcoding agent

    DeepSeek's open-weight coding model.

    No votes yet
    51.7/ 100 · provisional
    Why is DeepSeek V4 #10?
    Objective (hard data)weight 40%21.7/40
    Sentiment (votes)weight 40%provisional — not enough data
    Opinions (discussion)weight 20%provisional — not enough data

    Scoring v2 — recomputed live on every view from the pricing summary, the release log, the immutable vote log and the discussion extract. Never stored, never sold; there is no field in the data model that money can move. Public methodology →

    Full breakdown, cited events & pricing log →

  • 11
    Qwen 3.6Alibabacoding agentdata unverified

    Alibaba's open-weight coding models.

    No votes yet
    51.7/ 100 · provisional
    Why is Qwen 3.6 #11?
    Objective (hard data)weight 40%21.7/40
    Sentiment (votes)weight 40%provisional — not enough data
    Opinions (discussion)weight 20%provisional — not enough data

    Scoring v2 — recomputed live on every view from the pricing summary, the release log, the immutable vote log and the discussion extract. Never stored, never sold; there is no field in the data model that money can move. Public methodology →

    Full breakdown, cited events & pricing log →

  • 12
    GLM 5.2Zhipu AIcoding agent

    Zhipu's frontier open model.

    No votes yet
    51.5/ 100 · provisional
    Why is GLM 5.2 #12?
    Objective (hard data)weight 40%21.5/40
    Sentiment (votes)weight 40%provisional — not enough data
    Opinions (discussion)weight 20%provisional — not enough data

    Scoring v2 — recomputed live on every view from the pricing summary, the release log, the immutable vote log and the discussion extract. Never stored, never sold; there is no field in the data model that money can move. Public methodology →

    Full breakdown, cited events & pricing log →

  • 13
    Claude HaikuAnthropicllm modeldata unverified

    Anthropic's fast, low-cost model line.

    No votes yet
    50.0/ 100 · provisional
    Why is Claude Haiku #13?
    Objective (hard data)weight 40%provisional — not enough data
    Sentiment (votes)weight 40%provisional — not enough data
    Opinions (discussion)weight 20%provisional — not enough data

    Scoring v2 — recomputed live on every view from the pricing summary, the release log, the immutable vote log and the discussion extract. Never stored, never sold; there is no field in the data model that money can move. Public methodology →

    Full breakdown, cited events & pricing log →

  • 14
    Claude OpusAnthropicllm modeldata unverified

    Anthropic's frontier model line.

    No votes yet
    50.0/ 100 · provisional
    Why is Claude Opus #14?
    Objective (hard data)weight 40%provisional — not enough data
    Sentiment (votes)weight 40%provisional — not enough data
    Opinions (discussion)weight 20%provisional — not enough data

    Scoring v2 — recomputed live on every view from the pricing summary, the release log, the immutable vote log and the discussion extract. Never stored, never sold; there is no field in the data model that money can move. Public methodology →

    Full breakdown, cited events & pricing log →

  • 15
    Claude SonnetAnthropicllm modeldata unverified

    Anthropic's balanced workhorse model line.

    No votes yet
    50.0/ 100 · provisional
    Why is Claude Sonnet #15?
    Objective (hard data)weight 40%provisional — not enough data
    Sentiment (votes)weight 40%provisional — not enough data
    Opinions (discussion)weight 20%provisional — not enough data

    Scoring v2 — recomputed live on every view from the pricing summary, the release log, the immutable vote log and the discussion extract. Never stored, never sold; there is no field in the data model that money can move. Public methodology →

    Full breakdown, cited events & pricing log →

  • 16
    CommandCoherellm modeldata unverified

    Cohere's enterprise model line.

    No votes yet
    50.0/ 100 · provisional
    Why is Command #16?
    Objective (hard data)weight 40%provisional — not enough data
    Sentiment (votes)weight 40%provisional — not enough data
    Opinions (discussion)weight 20%provisional — not enough data

    Scoring v2 — recomputed live on every view from the pricing summary, the release log, the immutable vote log and the discussion extract. Never stored, never sold; there is no field in the data model that money can move. Public methodology →

    Full breakdown, cited events & pricing log →

  • 17
    DeepSeekDeepSeekllm modeldata unverified

    DeepSeek's open-weight model line.

    No votes yet
    50.0/ 100 · provisional
    Why is DeepSeek #17?
    Objective (hard data)weight 40%provisional — not enough data
    Sentiment (votes)weight 40%provisional — not enough data
    Opinions (discussion)weight 20%provisional — not enough data

    Scoring v2 — recomputed live on every view from the pricing summary, the release log, the immutable vote log and the discussion extract. Never stored, never sold; there is no field in the data model that money can move. Public methodology →

    Full breakdown, cited events & pricing log →

  • 18
    GeminiGooglellm modeldata unverified

    Google's frontier model line.

    No votes yet
    50.0/ 100 · provisional
    Why is Gemini #18?
    Objective (hard data)weight 40%provisional — not enough data
    Sentiment (votes)weight 40%provisional — not enough data
    Opinions (discussion)weight 20%provisional — not enough data

    Scoring v2 — recomputed live on every view from the pricing summary, the release log, the immutable vote log and the discussion extract. Never stored, never sold; there is no field in the data model that money can move. Public methodology →

    Full breakdown, cited events & pricing log →

  • 19
    GLMZ.ai (Zhipu AI)llm modeldata unverified

    Z.ai's frontier open model line.

    No votes yet
    50.0/ 100 · provisional
    Why is GLM #19?
    Objective (hard data)weight 40%provisional — not enough data
    Sentiment (votes)weight 40%provisional — not enough data
    Opinions (discussion)weight 20%provisional — not enough data

    Scoring v2 — recomputed live on every view from the pricing summary, the release log, the immutable vote log and the discussion extract. Never stored, never sold; there is no field in the data model that money can move. Public methodology →

    Full breakdown, cited events & pricing log →

  • 20
    GPT-5OpenAIllm modeldata unverified

    OpenAI's flagship general model line.

    No votes yet
    50.0/ 100 · provisional
    Why is GPT-5 #20?
    Objective (hard data)weight 40%provisional — not enough data
    Sentiment (votes)weight 40%provisional — not enough data
    Opinions (discussion)weight 20%provisional — not enough data

    Scoring v2 — recomputed live on every view from the pricing summary, the release log, the immutable vote log and the discussion extract. Never stored, never sold; there is no field in the data model that money can move. Public methodology →

    Full breakdown, cited events & pricing log →

  • 21
    GrokSpaceXAIllm modeldata unverified

    SpaceXAI's frontier model line (formerly xAI).

    No votes yet
    50.0/ 100 · provisional
    Why is Grok #21?
    Objective (hard data)weight 40%provisional — not enough data
    Sentiment (votes)weight 40%provisional — not enough data
    Opinions (discussion)weight 20%provisional — not enough data

    Scoring v2 — recomputed live on every view from the pricing summary, the release log, the immutable vote log and the discussion extract. Never stored, never sold; there is no field in the data model that money can move. Public methodology →

    Full breakdown, cited events & pricing log →

  • 22
    KimiMoonshot AIllm modeldata unverified

    Moonshot's frontier model line.

    No votes yet
    50.0/ 100 · provisional
    Why is Kimi #22?
    Objective (hard data)weight 40%provisional — not enough data
    Sentiment (votes)weight 40%provisional — not enough data
    Opinions (discussion)weight 20%provisional — not enough data

    Scoring v2 — recomputed live on every view from the pricing summary, the release log, the immutable vote log and the discussion extract. Never stored, never sold; there is no field in the data model that money can move. Public methodology →

    Full breakdown, cited events & pricing log →

  • 23
    LlamaMetallm modeldata unverified

    Meta's open-weight model line.

    No votes yet
    50.0/ 100 · provisional
    Why is Llama #23?
    Objective (hard data)weight 40%provisional — not enough data
    Sentiment (votes)weight 40%provisional — not enough data
    Opinions (discussion)weight 20%provisional — not enough data

    Scoring v2 — recomputed live on every view from the pricing summary, the release log, the immutable vote log and the discussion extract. Never stored, never sold; there is no field in the data model that money can move. Public methodology →

    Full breakdown, cited events & pricing log →

  • 24
    MistralMistral AIllm modeldata unverified

    Mistral's model line.

    No votes yet
    50.0/ 100 · provisional
    Why is Mistral #24?
    Objective (hard data)weight 40%provisional — not enough data
    Sentiment (votes)weight 40%provisional — not enough data
    Opinions (discussion)weight 20%provisional — not enough data

    Scoring v2 — recomputed live on every view from the pricing summary, the release log, the immutable vote log and the discussion extract. Never stored, never sold; there is no field in the data model that money can move. Public methodology →

    Full breakdown, cited events & pricing log →

  • 25
    Amazon NovaAmazonllm modeldata unverified

    AWS's in-house model line.

    No votes yet
    50.0/ 100 · provisional
    Why is Amazon Nova #25?
    Objective (hard data)weight 40%provisional — not enough data
    Sentiment (votes)weight 40%provisional — not enough data
    Opinions (discussion)weight 20%provisional — not enough data

    Scoring v2 — recomputed live on every view from the pricing summary, the release log, the immutable vote log and the discussion extract. Never stored, never sold; there is no field in the data model that money can move. Public methodology →

    Full breakdown, cited events & pricing log →

  • 26
    OpenAI o-seriesOpenAIllm modeldata unverified

    OpenAI's reasoning-model line.

    No votes yet
    50.0/ 100 · provisional
    Why is OpenAI o-series #26?
    Objective (hard data)weight 40%provisional — not enough data
    Sentiment (votes)weight 40%provisional — not enough data
    Opinions (discussion)weight 20%provisional — not enough data

    Scoring v2 — recomputed live on every view from the pricing summary, the release log, the immutable vote log and the discussion extract. Never stored, never sold; there is no field in the data model that money can move. Public methodology →

    Full breakdown, cited events & pricing log →

  • 27
    QwenAlibaballm modeldata unverified

    Alibaba's open-weight model line.

    No votes yet
    50.0/ 100 · provisional
    Why is Qwen #27?
    Objective (hard data)weight 40%provisional — not enough data
    Sentiment (votes)weight 40%provisional — not enough data
    Opinions (discussion)weight 20%provisional — not enough data

    Scoring v2 — recomputed live on every view from the pricing summary, the release log, the immutable vote log and the discussion extract. Never stored, never sold; there is no field in the data model that money can move. Public methodology →

    Full breakdown, cited events & pricing log →

  • 28
    Grok BuildxAIcoding agentdata unverified

    xAI's agentic coding surface.

    No votes yet
    48.7/ 100 · provisional
    Why is Grok Build #28?
    Objective (hard data)weight 40%18.7/40
    Sentiment (votes)weight 40%provisional — not enough data
    Opinions (discussion)weight 20%provisional — not enough data

    Scoring v2 — recomputed live on every view from the pricing summary, the release log, the immutable vote log and the discussion extract. Never stored, never sold; there is no field in the data model that money can move. Public methodology →

    Full breakdown, cited events & pricing log →