Best AI models for coding
The top AI models for real-world coding, ranked by the Artificial Analysis Coding Index — a composite score across coding benchmarks. Every one is available on anyAInow from a single balance; pay only for what you use, no subscription.
| # | Model | AA Coding Index | |
|---|---|---|---|
| 1 | Claude Opus 5 AnthropicFlagship·from $40 / 1M | 78 | Try → |
| 2 | GPT-5.6 Sol OpenAIFlagship·from $50 / 1M | 77.4 | Try → |
| 3 | GPT-5.6 Terra OpenAIBalanced·from $30 / 1M | 76.7 | Try → |
| 4 | Claude Fable 5 AnthropicFlagship·from $60 / 1M | 76.5 | Try → |
| 5 | Kimi K3 Moonshot (Kimi)Flagship·from $30 / 1M | 76.2 | Try → |
| 6 | GPT-5.5 OpenAIFlagship·from $50 / 1M | 74.9 | Try → |
| 7 | Claude Opus 4.8 AnthropicFlagship·from $30 / 1M | 74.3 | Try → |
| 8 | Grok 4.5 xAIFlagship·from $20 / 1M | 72.4 | Try → |
| 9 | Claude Sonnet 5 AnthropicBalanced·from $20 / 1M | 71.5 | Try → |
| 10 | GPT-5.6 Luna OpenAIFast·from $10 / 1M | 71.4 | Try → |
| 11 | GPT-5.4 OpenAIBalanced·from $30 / 1M | 71.1 | Try → |
| 12 | Gemini 3.5 Flash GoogleBalanced·from $20 / 1M | 70.1 | Try → |
| 13 | Gemini 3.1 Pro GoogleFlagship·from $20 / 1M | 68.8 | Try → |
| 14 | GLM 5.2 Z.ai (GLM)Open·from $10 / 1M | 68.8 | Try → |
| 15 | Qwen 3.7 Max QwenFlagship·from $10 / 1M | 66 | Try → |
| 16 | Claude Sonnet 4.6 AnthropicBalanced·from $30 / 1M | 63 | Try → |
| 17 | Kimi K2 Moonshot (Kimi)Balanced·from $10 / 1M | 61.8 | Try → |
| 18 | MiMo V2.5 Xiaomi (MiMo)Open·from $5 / 1M | 60.2 | Try → |
| 19 | DeepSeek V4 Pro DeepSeekOpen·from $10 / 1M | 59.4 | Try → |
| 20 | MiniMax M3 MiniMaxOpen·from $10 / 1M | 58.6 | Try → |
| 21 | DeepSeek V4 Flash DeepSeekFast·from $5 / 1M | 56.2 | Try → |
| 22 | GPT-5.4 mini OpenAIFast·from $10 / 1M | 56.1 | Try → |
| 23 | Qwen 3.7 Plus QwenOpen·from $10 / 1M | 55.9 | Try → |
| 24 | Qwen 3.6 Plus QwenOpen·from $10 / 1M | 54.5 | Try → |
| 25 | MiniMax M2.7 MiniMaxOpen·from $10 / 1M | 52.6 | Try → |
| 26 | Grok Build xAIFast·from $10 / 1M | 51.5 | Try → |
| 27 | Mistral Medium 3.5 MistralBalanced·from $20 / 1M | 46.9 | Try → |
| 28 | Claude Haiku 4.5 AnthropicFast·from $10 / 1M | 43.9 | Try → |
| 29 | Grok 4.3 xAIFlagship·from $10 / 1M | 42.2 | Try → |
| 30 | Gemini 3.1 Flash Lite GoogleFast·from $10 / 1M | 34.7 | Try → |
| 31 | Gemini 2.5 Pro GoogleFlagship·from $20 / 1M | 33.3 | Try → |
| 32 | Mistral Small 4 MistralFast·from $5 / 1M | 26.6 | Try → |
| 33 | Mistral Large 3 MistralFlagship·from $10 / 1M | 20.1 | Try → |
| 34 | Llama 4 Maverick Meta LlamaBalanced·from $10 / 1M | 16.3 | Try → |
| 35 | Llama 3.3 70B Meta LlamaFree·Free | 11.9 | Try → |
| 36 | Gemma 3 27B GoogleOpen·from $10 / 1M | 10.1 | Try → |
| 37 | Llama 4 Scout Meta LlamaOpen·from $5 / 1M | 8.2 | Try → |
Benchmarks via artificialanalysis.ai, as of 13 Aug 2026. Figures are publisher-reported where not independently verified. Prices shown are the anyAInow pay-as-you-go floor (per 1M tokens); free-tier models deduct nothing.