Model Comparisons.
The same builds, run on each new model, with what it cost.
NOV 10, 2026
Gemini 4 Carbon vs Argon: Is the Strongest Gemini Worth Switching To?
Google says to bring in Gemini 4 Carbon for your hardest problems. We gave Carbon and Argon the same seven jobs, from a messy email thread to a payroll function with eight hidden bugs. Argon matched it on every one, faster and for less.
AI for Mortals Staff
NOV 10, 2026
AI Model Cost Comparison: What the Same Build Cost on Claude, GPT-6, Gemini, Kimi and DeepSeek
Pat Simmons gave AI models the same builds, three to five at a time, and logged every run's cost, tokens and minutes. DeepSeek V4.1 Flash cost as little as $1.00 a build and Fable 5.1 as much as $592.37, and the two cheapest models placed low in the blind rankings. The page also lists every model's API price and the main plans, checked November 10, 2026.
Pat Simmons
NOV 10, 2026
Claude Fable 5.2 vs Opus 5.5: We Ran the Same Five Office Jobs on Both
Fable 5.2 costs twice as much per token as Opus 5.5. We gave both the same email thread, 48-page report, messy contact list, slide deck and small build. Three jobs were a tie, Fable won two on details, and it cost about twice as much to get there.
AI for Mortals Staff
NOV 9, 2026
Qwen vs ChatGPT: What Qwen 3.8 and GPT-6 Astra Do, What They Cost, and Who Each Is For
ChatGPT is OpenAI's all-in-one app, free or from $8 a month, with GPT-6 Astra on Plus and Pro. Qwen is Alibaba's free assistant and a family of open models you can download. Plans, sizes, licenses and Alibaba's own scores, from each company's pages.
Pat Simmons
NOV 9, 2026
Fable 5.2: No-Hype Full Review & Testing
Anthropic just released Fable 5.2, so I put it through three builds against Opus 5.5, Fable 5.1, GPT-6 Astra and Gemini 4 Argon, with the exact prompts and what every build cost.
Pat Simmons
NOV 9, 2026
Mistral vs Claude: Large 4 vs Opus 5.5 on Price, Coding and Which to Use
Mistral's Pro plan costs $14.99 a month and its flagship, Large 4, is open-weight; Claude Pro costs $20 and includes Claude Code. Plan prices, API rates and which to use for which job, from both companies' own pages.
Pat Simmons
NOV 9, 2026
Gemma vs Qwen: Gemma 4 vs Qwen 3.5, 3.6 and 3.8, Side by Side
Google's and Alibaba's own published numbers for Gemma 4 and Qwen 3.5, 3.6 and 3.8: coding scores, the sizes you can run at home, languages, audio and licenses.
Pat Simmons
NOV 8, 2026
AI Chatbot Subscriptions: What ChatGPT, Claude, Gemini and Grok Cost, Plan by Plan
Most AI chatbots are free to start and about $20 a month for the main paid plan. This guide lists what every ChatGPT, Claude, Gemini and Grok plan costs and includes, from each company's own pricing page.
Pat Simmons
NOV 6, 2026
Is ChatGPT Safe? What It Keeps, How to Lock It Down, and How Claude, Gemini, DeepSeek and Grok Compare
ChatGPT keeps what you type and, on its Free, Plus and Pro plans, can train on it until you switch that off. Each company's own privacy pages show what ChatGPT, Claude, Gemini, DeepSeek, Grok, Copilot, Perplexity and Meta AI keep, for how long, and which setting stops training on your chats.
Pat Simmons
NOV 6, 2026
Claude vs Gemini: Opus 5.5 vs Gemini 4 Argon on the Same Builds, and Which to Use for Each Job
Pat Simmons gave Claude's Opus 5.5 and Google's Gemini 4 Argon the same four builds and ranked them blind. Opus placed first every time and Argon last, Argon cost far less to run, and each starts on a plan of about $20 a month.
Pat Simmons
NOV 5, 2026
Claude vs ChatGPT vs Gemini: Opus 5.5, GPT-6 Astra and Gemini 4 Argon on the Same Builds
Pat Simmons gave Claude's Opus 5.5 and Fable 5.1, ChatGPT's GPT-6 Astra and Google's Gemini 4 Argon the same four builds and ranked them blind. Claude won every round, Gemini cost the least, and each top model starts on a plan of about $20 a month.
Pat Simmons
NOV 5, 2026
Gemini Omni 1.2 Flash, Tested: We Edited a Video Just by Chatting With It
Google's updated video model makes clips up to 15 seconds long with sound, costs 30% less, and lets you change a finished clip by typing what you want. We made ten clips with it. Swapping the scene worked every time we asked plainly. Changing the camera never did.
AI for Mortals Staff
NOV 5, 2026
Grok vs ChatGPT: Grok 4.7 and GPT-6 Astra on the Same 3 Builds, Plus What Each Plan Costs
Pat Simmons's tests put Grok 4.7 against ChatGPT's GPT-6 Astra on three identical builds and Grok Bot against ChatGPT's Dots on three agent jobs, next to what every plan costs.
Pat Simmons
NOV 5, 2026
Gemini vs ChatGPT: Gemini 4 Argon vs GPT-6 Astra on the Same 4 Builds
Pat Simmons gave Google's Gemini 4 Argon and ChatGPT's top model, GPT-6 Astra, the same four hard builds. Astra placed higher every time, and Argon cost about a tenth as much. Here is what each one costs and which plan gets it.
Pat Simmons
NOV 4, 2026
ChatGPT Alternatives: What Claude, Gemini, Grok, Meta AI, Copilot and Perplexity Do and Cost
Claude, Gemini, Grok, Meta's Muse, Copilot and Perplexity next to ChatGPT: what each one does, what it costs on its own pricing page, and where Pat Simmons's tests cover it.
Pat Simmons
NOV 2, 2026
Claude Sonnet vs Opus (and Haiku): Five Identical Builds, Ranked Blind, With the Cost of Every Run
Sonnet 5.5 and Opus 5.5 on the same five builds, three of them ranked blind, with the tokens, time and cost of every run, plus where Haiku 5.5 and Fable 5.1 fit.
Pat Simmons
OCT 25, 2026
Kimi K3.1 Pro Review: Is It Free, and Is It Any Good?
Kimi K3.1 Pro is free to try with limits, paid plans start at $15 a month, and the open weights are now on Hugging Face. In my three builds against Opus 5.5, Fable 5.1, GPT-6 Astra and DeepSeek V4.1 Flash, it came last every time.
Pat Simmons
OCT 14, 2026
Gemini 4 Argon Review: The Cheapest, and Last in Every Test
Google's newest frontier model is in the Gemini app for AI Pro and Ultra subscribers. I ran it through four hard builds against Opus 5.5, Fable 5.1 and GPT-6 Astra, ranked them blind, and tracked what each one cost.
Pat Simmons
OCT 12, 2026
Muse Wonder Review: Price, Access and 4 Builds vs Opus 5.5
What Meta's most capable model costs, which Muse or Muse Code plan gets you each version, and how Muse Wonder Full did against Opus 5.5, Fable 5.1 and GPT-6 Astra in four builds ranked blind.
Pat Simmons
OCT 12, 2026
AI Video Editing in Premiere Pro: How Claude Opus 5.5 Does 95% of My Edit (and How GPT-6 Astra Compares)
How I turned Opus 5.5 into my personal video editor: it edits every take inside Premiere Pro on a Mac Mini while I record the next one. The skill and the Premiere Pro bridge are free on GitHub.
Pat Simmons
OCT 7, 2026
Claude Haiku 5.5: What It Costs and How It Scores Against Sonnet 5.5 and GPT-6 Luna
Anthropic's smallest Claude model costs a tenth of Haiku 4.5's price on the API, is free to pick in the Claude app, and beats GPT-6 Luna in Anthropic's own tests while trailing Sonnet 5.5.
Pat Simmons
OCT 6, 2026
Grok Bot vs Meta Muse vs ChatGPT Dots: I Gave All Three the Same Jobs
I had all three plan a trip, research a YouTube video and run a fake coffee company for four hours. Grok Bot won every round.
Pat Simmons
SEP 29, 2026
Sonnet 5.5 Review: Five Builds Against Opus 5.5, With What Every Run Cost
Sonnet 5.5 against Opus 5.5, Fable 5.1, GPT-6 Astra and Sonnet 5 on the same builds, ranked blind, with the tokens, time and cost of every run.
Pat Simmons
SEP 25, 2026
Fable 5 Pricing: What Fable 5.1 Cost Against Opus 5.5 and GPT-6 Astra on the Same 3 Builds
Claude Fable 5 and 5.1 both cost $10 per million input tokens and $50 per million output. On the same three builds, Fable 5.1 cost $90.99 against $106.93 for Opus 5.5 and $60.20 for GPT-6 Astra, and Opus 5.5 won all three.
Pat Simmons
SEP 23, 2026
Opus 5.5 Review: Pricing and Real Builds vs Fable 5.1 and GPT-6 Astra
What Claude Opus 5.5 costs, where to get it, and how it did against Claude Fable 5.1 and GPT-6 Astra on four identical builds, ranked blind, with the cost of every run.
Pat Simmons
SEP 21, 2026
Grok 4.7
xAI's new coding model against Claude Fable 5.1 and GPT-6 Astra on three identical builds, with the cost of every run.
Pat Simmons
SEP 4, 2026
GPT-6 Astra vs Fable 5.1 vs GPT-5.6 Sol: Seven Builds and What Each One Cost
Seven builds in two rounds: Astra against Fable 5.1 on three, then GPT-5.6 Sol added on four more. Every prompt, every build, and what each one cost.
Pat Simmons
SEP 1, 2026
Fable 5.1 vs Fable 5 vs Opus 5
Anthropic says Fable 5.1 costs up to 45% less than Fable 5 on agentic work. I gave all three models the exact same five builds, let each pick its own concept, and logged the real tokens, cost, and time for every one.
Pat Simmons
JUL 24, 2026
Opus 5 vs Opus 4.8 vs Fable 5
Anthropic says Opus 5 is Fable 5 intelligence at half the price. I gave all three the exact same builds, let each pick its own concept, and logged the real tokens, cost, and time for every one.
Pat Simmons
JUL 22, 2026
Kimi K3 vs Fable 5 vs GPT-5.6
I gave Kimi K3, Fable 5, and GPT-5.6 the exact same builds, one-shot, and logged the real cost and time. The cheap open-source model held up shockingly well, at a fraction of Fable's price.
Pat Simmons
JUL 20, 2026
GLM 5.2 vs Kimi K3: Which Cheap Coding Model Actually Wins?
I gave two of the cheapest strong coding models the same six jobs. Which one is cheaper flips completely depending on the work, and there's a simple rule for which to use when.
Pat Simmons
JUL 8, 2026
Grok 4.5 Launches, Pitched as Opus-Class for a Fraction of the Cost
Elon Musk's xAI is pitching top-tier coding and agent work at a fraction of what OpenAI and Anthropic charge.
Pat Simmons
