Model comparisons
Which model, and what it costs
to finish the job.
Every pair I have run, indexed by model. Published price, the independent score, and the number that decides it in practice: what one finished task cost, not what a million tokens list for.
28 comparisons across 24 models. Each one is rewritten when the numbers move, not left to rot.
01 Oct 2026 · 7 min read
28 Sept 2026 · 8 min read
Claude Sonnet 5.5 scores 18 points more than Sonnet 5 and the list price did not move
01 Oct 2026 · 6 min readGPT-6.1 Sol scores four points more than GPT-6 Sol, halves the cache price, and lands one point behind Astra
Claude Opus 5.5 beats GPT-6 Astra on every score and still costs more to finish the job
Pick the model you run
Models you can buy today. Each one lists what I have measured it against.
Claude Fable 5.1
Anthropic · 4 comparisonsClaude Haiku 4.5
Anthropic · 3 comparisonsClaude Opus 5.5
Anthropic · 3 comparisonsClaude Code
Anthropic · 1 comparisonClaude Mythos 5.1
Anthropic · 1 comparisonClaude Sonnet 5.5
Anthropic · 1 comparisonGPT-6 Astra
OpenAI · 5 comparisonsCodex
OpenAI · 1 comparisonGPT-6 Luna
OpenAI · 1 comparisonGPT-6.1 Sol
OpenAI · 1 comparisonGemini 3.8 Flash
Google · 2 comparisonsMuse Spark 1.3
Meta · 1 comparisonGrok 4.6
xAI · 1 comparisonDeepSeek V4.1 Flash
DeepSeek · 1 comparisonModels that have been replaced
Still here, because people run what they already bought. Each article says what took its place.
Claude Sonnet 5
GPT-5.6 Luna
Claude Sonnet 4.6
GPT-5.6 Terra
Claude Mythos 5
Claude Opus 4.8
In the order I ran them
Newest first, with the verdict on one line.
PairWhat it comes down toDate
Claude Sonnet 5.5vsClaude Sonnet 5same price, 18 points01 Oct 20267 min readGPT-6.1 SolvsGPT-6 Solfour points up, cache cut in half01 Oct 20266 min readGPT-6 AstravsClaude Opus 5.5better and dearer per task28 Sept 20268 min readClaude Opus 5.5vsOpus 5cheaper per token, dearer per task23 Sept 20269 min readGPT-6 LunavsClaude Haiku 4.51/10 price, 2x the score23 Sept 20267 min readGPT-6 SolvsClaude Opus 5.5the index and the invoice disagree23 Sept 20268 min readGPT-6 SolvsGPT-6 Astraties on code, loses the terminal23 Sept 20267 min readClaude CodevsCodexcoding agent benchmark and cost16 Sept 20267 min readClaude Fable 5.1vsFable 5what changed, what breaks16 Sept 20267 min readClaude Haiku 4.5vsGPT-5.6 Luna5x price, 20 points behind16 Sept 20266 min readThe systems behind these numbers are the actual work.
Model choice is one decision inside a revenue system. The rest of what I build and run is in the field notes.
Read the field notes →