BENCHMARK 1 · SLOTKEEPER BOOKING APP · TESTED OCT 14–25, 2026 · ONE RUN PER TOOL How we test →

Home / Categories

Do you even need the specialist tool?

Most people already pay for ChatGPT, Claude, Grok or Gemini. So every category we test now gives those four general agents the same task as the specialist tools, and scores every tool on its free plan and its cheapest paid plan.

NoteOur first category (AI app builders) ran before this rule: specialists only, free plans only. The general agents and paid plans are added at the retest. The order below is a draft; nothing in a planned category has been run, so there are no dates or scores for them yet.

DONE

AI app builders

Do you even need an AI app builder, or will a chatbot do?

Tested
Bolt.new, Base44, v0, Lovable, Replit Agent, Cursor (reference)
General agents
ChatGPT measured through its coding agent, Codex (82.5, baseline). Claude, Grok and Gemini not tested yet.

See the results →

PLANNED

AI coding agents

Do you even need a coding agent, or is a chatbot enough?

Candidates (to confirm on test day)
Cursor, GitHub Copilot, Codex, Claude Code, Gemini CLI
General agents
Baseline: ChatGPT · Claude · Grok · Gemini, on free and cheapest paid plans.

PLANNED

AI website builders

Do you even need an AI website builder?

Candidates (to confirm on test day)
Wix, Framer, Hostinger Horizons, Durable
General agents
Baseline: ChatGPT · Claude · Grok · Gemini, on free and cheapest paid plans.

PLANNED

Automation agents

Do you even need Zapier anymore?

Candidates (to confirm on test day)
Zapier, Make, n8n, Lindy
General agents
Baseline: ChatGPT · Claude · Grok · Gemini, on free and cheapest paid plans.

Read the 7-day test plan →

PLANNED

Deck makers

Do you even need an AI deck maker?

Candidates (to confirm on test day)
Gamma, Beautiful.ai, Canva, Pitch
General agents
Baseline: ChatGPT · Claude · Grok · Gemini, on free and cheapest paid plans.

PLANNED

App-builder retest

Do you even need an AI app builder? The retest adds the general agents and paid plans.

Candidates (to confirm on test day)
Bolt.new, Base44, v0, Lovable, Replit Agent, Emergent
General agents
Baseline: ChatGPT · Claude · Grok · Gemini, on free and cheapest paid plans.

How the baseline and the two plans are scored →