{
  "version": "https://jsonfeed.org/version/1.1",
  "title": "The Pack · VerdictPal",
  "home_page_url": "https://verdictpal.com/pack",
  "feed_url": "https://verdictpal.com/feed.json",
  "description": "Editorial drops when a tool ships, verdicts move, or methodology changes.",
  "language": "en-US",
  "authors": [
    {
      "name": "VerdictPal editorial desk",
      "url": "https://verdictpal.com/about"
    }
  ],
  "items": [
    {
      "id": "2026-10-07-claude-haiku-5-5",
      "url": "https://verdictpal.com/models/claude-haiku-5-5",
      "title": "Claude Haiku 5.5 is on the atlas — $0.10 / $0.50 up to 100k tokens",
      "content_text": "Anthropic's 7 Oct launch. API id claude-haiku-5-5. Short prompts are $0.10 in / $0.50 out per 1M tokens; over 100k, $0.50 / $2.50. First Haiku with adjustable effort. Launch-table scores stay off the ledger. /models/claude-haiku-5-5",
      "date_published": "2026-10-07T00:00:00.000Z",
      "tags": [
        "models"
      ]
    },
    {
      "id": "2026-09-29-gpt-6-1-sol",
      "url": "https://verdictpal.com/models/gpt-6-1-sol",
      "title": "GPT-6.1 Sol is on the atlas",
      "content_text": "Recorded from the OpenAI API on 29 Sep. Text and image in, 1.05M context, 128K output, knowledge cutoff 30 Apr 2026. /models/gpt-6-1-sol",
      "date_published": "2026-09-29T00:00:00.000Z",
      "tags": [
        "models"
      ]
    },
    {
      "id": "2026-09-28-claude-sonnet-5-5",
      "url": "https://verdictpal.com/models/claude-sonnet-5-5",
      "title": "Claude Sonnet 5.5 is on the atlas",
      "content_text": "Recorded from the Claude Platform on 28 Sep. Text and image in, 1M context, 128K output. /models/claude-sonnet-5-5",
      "date_published": "2026-09-28T00:00:00.000Z",
      "tags": [
        "models"
      ]
    },
    {
      "id": "2026-09-23-frontier-launches",
      "url": "https://verdictpal.com/models",
      "title": "Opus 5.5, GPT-6 Sol and Luna, Grok 4.7, and MiMo-V2.6 are on the atlas",
      "content_text": "Recorded from vendor docs on 23 Sep. Anthropic, OpenAI, xAI, and Xiaomi each shipped a public model in the prior four days. List price, context, and modalities are on the model pages. Sonnet 5.5 and Haiku 5.5 are not released. /models",
      "date_published": "2026-09-23T00:00:00.000Z",
      "tags": [
        "models"
      ]
    },
    {
      "id": "2026-09-14-pricing-privacy-refresh",
      "url": "https://verdictpal.com/tools",
      "title": "Live pricing pass: Consensus Pro $20, Gumloop credits, Canva yearly, Mistral Student $5.99",
      "content_text": "Vendor pages re-checked 14 Sep. Consensus Pro is $20/mo or $144/yr. Gumloop dropped the Free 5k and $97 Pro SKUs — Pro starts at $37/20k credits. Canva Pro is US$144/year, Business US$250/year/person. Mistral Education is $5.99. Scholarcy Library is $9.99/mo or $90/year. /tools",
      "date_published": "2026-09-14T00:00:00.000Z",
      "tags": [
        "tools"
      ]
    },
    {
      "id": "2026-09-12-vals-v2-deepseek-flash",
      "url": "https://verdictpal.com/models",
      "title": "DeepSeek V4.1 Flash is on the model atlas",
      "content_text": "DeepSeek's 10 Sep V4.1 Flash is recorded from the official launch: 552B MoE, deepseek-flash, off-peak $0.15 / $0.60. The Vals Index page is no longer on the atlas. /models",
      "date_published": "2026-09-12T00:00:00.000Z",
      "tags": [
        "models"
      ]
    },
    {
      "id": "2026-09-10-aa-index-v43",
      "url": "https://verdictpal.com/benchmarks/terminal-bench",
      "title": "Terminal-Bench stays on published 2.1 and Hard",
      "content_text": "The Artificial Analysis intelligence index is not a VerdictPal page. Terminal-Bench on the atlas is the published 2.1 and Hard suites. /benchmarks/terminal-bench",
      "date_published": "2026-09-10T00:00:00.000Z",
      "tags": [
        "benchmarks"
      ]
    },
    {
      "id": "2026-09-05-frontier-september",
      "url": "https://verdictpal.com/models",
      "title": "September 2026 frontier: GPT-6 Astra, Gemini 3.8 Flash, Muse Spark 1.3, Hy4 preview",
      "content_text": "OpenAI's 3 Sep GPT-6 Astra, Google's 2 Sep Gemini 3.8 Flash, and Meta's 2 Sep Muse Spark 1.3 are now on the atlas. Tencent's Hy4 preview is recorded from the official launch. /models",
      "date_published": "2026-09-05T00:00:00.000Z",
      "tags": [
        "models"
      ]
    },
    {
      "id": "2026-09-01-claude-fable-5-1",
      "url": "https://verdictpal.com/models/claude-fable-5-1",
      "title": "Claude Fable 5.1 is on the model atlas",
      "content_text": "Anthropic's 1 Sep Mythos-class refresh of Fable 5. Same $10 / $50 list, cache reads cut to $0.25 per 1M tokens. Compare it with GPT-5.6 Sol or Fable 5. /models/claude-fable-5-1",
      "date_published": "2026-09-01T00:00:00.000Z",
      "tags": [
        "models"
      ]
    },
    {
      "id": "2026-09-01-omniscience-critpt",
      "url": "https://verdictpal.com/benchmarks",
      "title": "AA-Omniscience and CritPt join the benchmark atlas",
      "content_text": "AA-Omniscience (factual recall vs hallucination — the knowledge primary) and CritPt (research-level physics) now have explainers and sourced rows. /benchmarks/aa-omniscience · /benchmarks/critpt",
      "date_published": "2026-09-01T00:00:00.000Z",
      "tags": [
        "benchmarks"
      ]
    },
    {
      "id": "2026-08-27-terminal-bench-science",
      "url": "https://verdictpal.com/benchmarks/terminal-bench-science",
      "title": "Terminal-Bench-Science 0.1 is on the atlas — best row 30%",
      "content_text": "Stanford and Laude's 70-task science-agent suite: real lab workflows, still far from ceiling. Claude Opus 5 + Claude Code leads at 30.0%; GPT-5.6 Sol + Codex is 22.4%; GLM-5.3 is the strongest open-weight row at 8.1%. Not Terminal-Bench 2.1. /benchmarks/terminal-bench-science",
      "date_published": "2026-08-27T00:00:00.000Z",
      "tags": [
        "benchmarks"
      ]
    },
    {
      "id": "2026-08-26-glm-5-3-flash",
      "url": "https://verdictpal.com/models/glm-5-3-flash",
      "title": "GLM-5.3-Flash is on the model atlas",
      "content_text": "Z.ai's Flash sibling of GLM-5.3, from the 1 Sep Artificial Analysis snapshot: $0.15 / $0.50 per 1M tokens. /models/glm-5-3-flash · /compare/models/glm-5-3-vs-glm-5-3-flash",
      "date_published": "2026-08-26T00:00:00.000Z",
      "tags": [
        "models"
      ]
    },
    {
      "id": "2026-08-27-academic-guides",
      "url": "https://verdictpal.com/guides",
      "title": "Three academic guide trios, rebuilt",
      "content_text": "Student researcher, literature reviewer, and peer reviewer — each with a matching stack and playbook. Peer review starts with the venue AI policy. Retired grant, coding, and deck paths redirect to /guides.",
      "date_published": "2026-08-27T00:00:00.000Z",
      "tags": [
        "guide"
      ]
    },
    {
      "id": "2026-08-24-glm-5-3",
      "url": "https://verdictpal.com/models/glm-5-3",
      "title": "GLM-5.3 is on the model atlas",
      "content_text": "Z.ai's August coding refresh is on the atlas from the 2026-08-24 Artificial Analysis snapshot: API list $1.40 / $4.40 per 1M tokens. Same base as GLM-5.2; weights were still unpublished on this check. Ledger rows sync from AA; editorial depth still needs a desk pass. Compare it with Qwen3.8 27B. /models/glm-5-3 · /compare/models/glm-5-3-vs-qwen3-8-27b",
      "date_published": "2026-08-24T00:00:00.000Z",
      "tags": [
        "models"
      ]
    },
    {
      "id": "2026-08-24-qwen3-8-27b",
      "url": "https://verdictpal.com/models/qwen3-8-27b",
      "title": "Qwen3.8 27B is on the model atlas",
      "content_text": "Alibaba's dense open-weight Qwen3.8 sibling is on the atlas from the 2026-08-24 Artificial Analysis snapshot: hosted list $0.50 / $3 per 1M tokens, Apache 2.0 on Hugging Face. This is not hosted Qwen3.8 Max. Ledger rows sync from AA; editorial depth still needs a desk pass. Compare it with Qwen3.8 Max. /models/qwen3-8-27b · /compare/models/qwen3-8-27b-vs-qwen3-8-max",
      "date_published": "2026-08-24T00:00:00.000Z",
      "tags": [
        "models"
      ]
    },
    {
      "id": "2026-08-15-qwen3-8-2-4t",
      "url": "https://verdictpal.com/models/qwen3-8-2-4t-a95b",
      "title": "Qwen3.8 2.4T is on the model atlas",
      "content_text": "Alibaba's open-weight Qwen-Max-class MoE (2.4T total / 95B active) is on the atlas from the 2026-08-15 Artificial Analysis snapshot: hosted list $2 / $6 per 1M tokens. This is the published checkpoint, not hosted Qwen3.8 Max. Ledger rows sync from AA; editorial depth still needs a desk pass. Compare it with Qwen3.8 Max. /models/qwen3-8-2-4t-a95b · /compare/models/qwen3-8-2-4t-a95b-vs-qwen3-8-max",
      "date_published": "2026-08-15T00:00:00.000Z",
      "tags": [
        "models"
      ]
    },
    {
      "id": "2026-08-13-gemini-3-7-flash",
      "url": "https://verdictpal.com/models/gemini-3-7-flash",
      "title": "Gemini 3.7 Flash is on the model atlas",
      "content_text": "Google's August Flash workhorse is on the atlas from the Artificial Analysis snapshot: intro price $0.75 / $3.75 per 1M tokens through 31 Dec 2026. Ledger rows sync from AA; editorial depth still needs a desk pass. Compare it with 3.6 Flash or Claude Sonnet 4.6. /models/gemini-3-7-flash · /compare/models/gemini-3-6-flash-vs-gemini-3-7-flash",
      "date_published": "2026-08-13T00:00:00.000Z",
      "tags": [
        "models"
      ]
    },
    {
      "id": "2026-08-12-grok-4-6",
      "url": "https://verdictpal.com/models/grok-4-6",
      "title": "Grok 4.6 is on the model atlas",
      "content_text": "xAI's August flagship is on the atlas from the Artificial Analysis snapshot: $2 / $6 per 1M tokens. Ledger rows sync from AA; editorial depth still needs a desk pass. Compare it with GPT-5.6 Sol. /models/grok-4-6 · /compare/models/gpt-5-6-sol-vs-grok-4-6",
      "date_published": "2026-08-12T00:00:00.000Z",
      "tags": [
        "models"
      ]
    },
    {
      "id": "2026-08-03-launch-and-atlas-report",
      "url": "https://verdictpal.com/report",
      "title": "VerdictPal is live, and the Atlas Report puts numbers on the whole atlas",
      "content_text": "The launch note is published, plus a new original-research surface: the Atlas Report computes aggregate pricing, privacy, benchmark-saturation and freshness figures from every published tool, and it is free to cite with a link. Highlights this edition — most dossiers do not record any stance on training with your content, paid entry plans cluster around the median, and frontier model input prices spread by more than three orders of magnitude. /report · /launch",
      "date_published": "2026-08-03T00:00:00.000Z",
      "tags": [
        "desk"
      ]
    },
    {
      "id": "2026-07-12-ai-builder-design-test",
      "url": "https://verdictpal.com/benchmarks/lab",
      "title": "The public Lab page is Citation Fidelity",
      "content_text": "The design-test page is gone. Citation Fidelity stays on the Lab desk, and those scores stay unpublished. /benchmarks/lab",
      "date_published": "2026-07-12T00:00:00.000Z",
      "tags": [
        "bench"
      ]
    },
    {
      "id": "2026-07-06-citation-fidelity-protocol-freeze",
      "url": "https://verdictpal.com/benchmarks/citation-fidelity",
      "title": "Citation Fidelity v0.1 protocol frozen on the Lab bench",
      "content_text": "VerdictPal Lab's first first-party benchmark: twelve research questions, dual-reviewer citation grading, frozen runbook on the atlas page — protocol published, desk run still pending, no padded leaderboard. /benchmarks/citation-fidelity · /benchmarks/lab",
      "date_published": "2026-07-06T00:00:00.000Z",
      "tags": [
        "bench"
      ]
    },
    {
      "id": "2026-07-02-research-guides-batch",
      "url": "https://verdictpal.com/guides",
      "title": "Five research guides now on the atlas",
      "content_text": "Citation audit, systematic review protocol, data cleaning pipeline, grant writer path, and peer reviewer path — solid guides with step blocks and verification checklists.",
      "date_published": "2026-07-02T00:00:00.000Z",
      "tags": [
        "guide"
      ]
    },
    {
      "id": "2026-06-25-student-research-workflow",
      "url": "https://verdictpal.com/guides/trusted-source-brief",
      "title": "Student research workflow on the guides pillar",
      "content_text": "Path, stack, playbook, and showcase for turning broad prompts into source-backed briefs — the workflow we point new readers at first.",
      "date_published": "2026-06-25T00:00:00.000Z",
      "tags": [
        "guide"
      ]
    },
    {
      "id": "2026-06-24-factory-flagship",
      "url": "https://verdictpal.com/tools/factory",
      "title": "Factory flagship dossier shipped",
      "content_text": "Agent-native delivery with Droid, Spec Mode, missions, and enterprise controls — fit 74 with the autonomy and pricing caveats on the record.",
      "date_published": "2026-06-24T00:00:00.000Z",
      "tags": [
        "tool"
      ]
    },
    {
      "id": "2026-06-23-cursor-flagship",
      "url": "https://verdictpal.com/tools/cursor",
      "title": "Cursor flagship dossier shipped",
      "content_text": "VS Code-compatible AI editor at fit 81 — Tab, Chat, Agent, Privacy Mode, team governance, and the diff-review failure modes we publish before you merge.",
      "date_published": "2026-06-23T00:00:00.000Z",
      "tags": [
        "tool"
      ]
    },
    {
      "id": "2026-06-22-gemini-flagship",
      "url": "https://verdictpal.com/tools/gemini",
      "title": "Gemini flagship dossier shipped",
      "content_text": "Google's multimodal assistant ecosystem at fit 75 — Search grounding, Deep Research, storage bundles, and where it is not a cited search engine.",
      "date_published": "2026-06-22T00:00:00.000Z",
      "tags": [
        "tool"
      ]
    },
    {
      "id": "2026-06-21-notebooklm-flagship",
      "url": "https://verdictpal.com/tools/notebooklm",
      "title": "NotebookLM flagship dossier shipped",
      "content_text": "Source-grounded reading workspace at fit 78 — corpus chat, Audio Overviews, Flashcards, and the empty-corpus trap documented on the dossier.",
      "date_published": "2026-06-21T00:00:00.000Z",
      "tags": [
        "tool"
      ]
    },
    {
      "id": "2026-06-20-perplexity-flagship",
      "url": "https://verdictpal.com/tools/perplexity",
      "title": "Perplexity flagship dossier shipped",
      "content_text": "Cited search front door at fit 72 — consumer Pro/Max, Deep Research, Sonar APIs, and failure modes for bibliographies you have not opened.",
      "date_published": "2026-06-20T00:00:00.000Z",
      "tags": [
        "tool"
      ]
    },
    {
      "id": "2026-06-15-opencode-flagship",
      "url": "https://verdictpal.com/tools/opencode",
      "title": "OpenCode flagship dossier shipped",
      "content_text": "The open-source coding agent at fit 95 — Plan/Build modes, Go and Zen pricing, 75+ providers, and the free-model privacy caveats on the record.",
      "date_published": "2026-06-15T00:00:00.000Z",
      "tags": [
        "tool"
      ]
    },
    {
      "id": "2026-06-15-command-code-flagship",
      "url": "https://verdictpal.com/tools/command-code",
      "title": "Command Code flagship dossier shipped",
      "content_text": "Terminal coding agent with taste-1 learning, open-model deals from $1/mo, and the full pricing and privacy picture — including what lives in .commandcode/.",
      "date_published": "2026-06-15T00:00:00.000Z",
      "tags": [
        "tool"
      ]
    },
    {
      "id": "2026-06-15-raycast-flagship",
      "url": "https://verdictpal.com/tools/raycast",
      "title": "Raycast flagship dossier shipped",
      "content_text": "The macOS launcher we install before debating another AI tab — extensions, Quick AI, clipboard, and honest failure modes at fit 97.",
      "date_published": "2026-06-15T00:00:00.000Z",
      "tags": [
        "tool"
      ]
    },
    {
      "id": "2026-06-08-grant-deadline-set",
      "url": "https://verdictpal.com/guides",
      "title": "Grant deadline set (archived)",
      "content_text": "The grant-deadline path has been retired. Academic guides now live as three trios: student researcher, literature reviewer, and peer reviewer.",
      "date_published": "2026-06-08T00:00:00.000Z",
      "tags": [
        "guide"
      ]
    },
    {
      "id": "2026-06-02-trusted-source-brief",
      "url": "https://verdictpal.com/guides/trusted-source-brief",
      "title": "Trusted-source brief workflow shipped",
      "content_text": "The Guides pillar now has a real student research path, tool stack, playbook, and showcase for turning broad prompts into source-backed briefs.",
      "date_published": "2026-06-02T00:00:00.000Z",
      "tags": [
        "guide"
      ]
    },
    {
      "id": "2026-06-02-dark-mode-polish",
      "url": "https://verdictpal.com/brand",
      "title": "Dark mode rebuilt for the evidence instrument",
      "content_text": "Dark surfaces now use muted amber, readable borders, and component-specific overrides instead of neon panels and inverted cream panels.",
      "date_published": "2026-06-02T00:00:00.000Z",
      "tags": [
        "design"
      ]
    }
  ]
}