/best/codingupdated May 202616 models evaluated

Best AI for coding

Writing new code, debugging, refactoring, and reviewing pull requests.

CodingMathWritingResearchTranslationData AnalysisChatbotsStudentsBusinessCreative WritingTabular Data & Spreadsheets

Coding has become the single most important task for production AI. Agents commit code. IDEs rely on models for tab completion, multi-file edits, and test generation. The cost of a wrong answer compounds — a model that hallucinates an API gets wedged into a codebase and quietly ships.

What matters: correctness on held-out tests (SWE-bench, LiveCodeBench), diff-style edit fidelity, tool-use fluency (shell, file I/O, search), and the ability to reason about a large context without losing the plot. Speed matters too — autocomplete needs to fire in under 400ms to feel natural.

Our coding rank weights SWE-bench Verified (60%), multi-file edit accuracy (25%), and tool-use reliability (15%). If you're building an autonomous coding agent, weight reasoning and tool-use more heavily. For interactive autocomplete, speed becomes the deciding factor.

Full rankings

All 16 models, scored for coding

weighted composite · lower-is-worse
#ModelProviderTask score$/in$/outContext
01Claude Opus 4.7AAnthropic83.5%$5.00$25.001M
02GPT-5.5OOpenAI80.6%$5.00$30.001.1M
03Claude Opus 4.6AAnthropic78.7%$5.00$25.001M
04GPT-5.4OOpenAI76.9%$2.50$15.001.1M
05MoonshotAI: Kimi K2.6MMoonshotAI76.7%$0.730$3.49262K
06Gemini 3 Flash PreviewGGoogle75.4%$0.500$3.001.0M
07Claude Sonnet 4.6AAnthropic75.2%$3.00$15.001M
08GPT-5.2OOpenAI73.8%$1.75$14.00400K
09GPT-5OOpenAI73.6%$1.25$10.00400K
10GPT-5.1OOpenAI68.0%$1.25$10.00400K
11GPT-5 MiniOOpenAI64.7%$0.250$2.00400K
12o3OOpenAI62.3%$2.00$8.00200K
13Qwen: Qwen3.6 PlusQQwen57.9%$0.325$1.951M
14Gemini 2.5 ProGGoogle57.6%$1.25$10.001.0M
15GPT-4.1OOpenAI48.5%$2.00$8.001.0M
16GPT-4oOOpenAI31.0%$2.50$10.00128K

Pricing — top 5 for coding

AClaude Opus 4.7
$20.00/MTok
83.5%
OGPT-5.5
$23.75/MTok
80.6%
AClaude Opus 4.6
$20.00/MTok
78.7%
OGPT-5.4
$11.88/MTok
76.9%
MMoonshotAI: Kimi K2.6
$2.80/MTok
76.7%
modelpicker.aipowered by live benchmark data

The best AI for coding changes every month.

We'll email you when rankings shift, new models hit the top 5, or pricing cuts reshuffle the value leaders.

Get notified when models change
Price drops, new models, benchmark updates. One email per change, no spam.