Best of
Best AI for coding
For programming help, Claude Opus 5.5 is our pick when quality matters most, and Claude Sonnet 5.5 is the better value.
Costs here use the prices AI companies charge software developers, so they show relative cost, not your monthly bill. See what ChatGPT, Claude and Gemini charge you.
| Model and our take (editorial) | Type | Smartness | Reads at once* | Essay | Chat | |
|---|---|---|---|---|---|---|
| Claude Sonnet 5.5 The sensible default: close to the top tier for writing, fixing code and everyday work, at about half the price of Claude Opus 5.5. | Most capable | ★★★★★ | 1,500 pages | $0.01 | $2.62 | $0.07 |
| Claude Opus 5.5 The strongest all-round pick when quality matters more than cost, especially for big, complicated jobs like long coding projects. | Most capable | ★★★★★ | 1,500 pages | $0.03 | $5.25 | $0.15 |
| GPT-6.1 Sol Good value from OpenAI: strong at programming and working through long documents, at a mid-range price. | Most capable | ★★★★★ | 1,580 pages | $0.01 | $2.62 | $0.07 |
| Grok 4.7 Grok's top model, aimed at programming and long, multi-step jobs, priced below most top models. | Most capable | ★★★★☆ | 750 pages | $0.01 | $2.54 | $0.07 |
| Muse Spark Open A downloadable Meta model tuned for programming. The one to watch if you want to run your own coding helper. | Free to downloadfree to download | Not rated yet | 1,570 pages | $0.01 | $1.60 | $0.04 |
| Kimi K3 A very large downloadable model for complicated programming and long jobs. | Free to downloadfree to download | ★★★★☆ | 1,570 pages | $0.02 | $0.61 | $0.02 |
How we chose: Editorial shortlist. We have not run our own coding tests yet.
Why each one
Claude Sonnet 5.5
The sensible default: close to the top tier for writing, fixing code and everyday work, at about half the price of Claude Opus 5.5.
The sensible default: close to the top tier for writing, fixing code and everyday work, at about half the price of Claude Opus 5.5.
Claude Opus 5.5
The strongest all-round pick when quality matters more than cost, especially for big, complicated jobs like long coding projects.
The strongest all-round pick when quality matters more than cost, especially for big, complicated jobs like long coding projects.
GPT-6.1 Sol
Good value from OpenAI: strong at programming and working through long documents, at a mid-range price.
Good value from OpenAI: strong at programming and working through long documents, at a mid-range price.
Grok 4.7
Grok's top model, aimed at programming and long, multi-step jobs, priced below most top models.
Grok's top model, aimed at programming and long, multi-step jobs, priced below most top models.
Muse Spark Open
A downloadable Meta model tuned for programming. The one to watch if you want to run your own coding helper.
A downloadable Meta model tuned for programming. The one to watch if you want to run your own coding helper.
Kimi K3
A very large downloadable model for complicated programming and long jobs.
A very large downloadable model for complicated programming and long jobs.