AI Coding Models
Models specifically optimized for code generation, debugging, refactoring, and software development tasks.
45 models in this category.
Stable Code 3B
Stability AIStability AI's code-focused model. Small, efficient model for code completion and generation.
Microsoft Phi-4
MicrosoftMicrosoft's compact 14B model with strong reasoning and coding capability. Excellent value for small-scale deployments.
Gemma 3 27B
GoogleGoogle's open-weight 27B model. Budget-friendly with strong coding capability and Google's research backing.
Phi-4 Mini
MicrosoftMicrosoft's latest small model with improved coding ability. Better than Phi-3 for developer tasks.
DeepSeek V3
DeepSeekDeepSeek's latest general model. Competitive with Claude Sonnet at a fraction of the cost.
DeepSeek R1
DeepSeekDeepSeek's reasoning model. Open-weight model that rivals o1 for complex reasoning tasks.
Mistral Nemo
MistralCompact 12B open-weight model co-developed with NVIDIA. Excellent coding performance at minimal cost.
Qwen 2.5 Coder 32B
QwenQwen's code-specialized 32B model. Trained on 130+ programming languages.
Llama 3.1 70B
MetaMeta's mid-size Llama 3.1. Strong general performance with open weights for custom deployment.
Qwen Coder Turbo
QwenFast coding model from Qwen. Good price-performance for code generation.
Llama 3.3 70B
MetaMeta's open-weight 70B model. Strong coding and general capability, widely supported across AI platforms.
DeepSeek Coder V2
DeepSeekDeepSeek's coding-specialized model. Open-source and very affordable.
DeepSeek Coder V3
DeepSeekLatest generation DeepSeek coding model. Improved code understanding and generation over V2.
Codestral
MistralMistral's dedicated coding model. Open-weight and highly optimized for code generation and completion.
Qwen Coder Turbo V2
QwenUpdated Qwen Coder Turbo with improved code generation quality. Strong value for budget coding.
Mistral Medium
MistralMid-tier Mistral model between Small and Large. Strong coding capability at a moderate price point.
GPT-4.1 mini
OpenAICost-optimized GPT-4.1 variant. Strong coding capability at budget pricing, replacing GPT-4o mini for many use cases.
Qwen 2.5 72B
QwenQwen's open-weight 72B model. Strong Chinese and English performance at competitive pricing.
Llama 4 Maverick
MetaMeta's Llama 4 flagship model. Strong multimodal and coding with MoE architecture.
Qwen 3 Coder
QwenLatest Qwen coding-specialized model. Strong performance on HumanEval and competitive programming benchmarks.
Groq Llama 3.3 70B
GroqLlama 3.3 70B running on Groq's ultra-fast LPU inference. Sub-100ms responses for 70B model.
GLM-4-Plus
Zhipu AIZhipu AI's balanced model. Strong Chinese language understanding with competitive coding ability.
Databricks DBRX Instruct
DatabricksDatabricks' open MoE model. Competitive with GPT-3.5 for coding and general tasks.
Qwen Coder Plus
QwenQwen model specifically optimized for coding tasks.
Together Llama 3.3 70B
Together AILlama 3.3 70B via Together AI. Cost-effective inference for open models.
OpenAI o3-mini
OpenAIAffordable reasoning model for coding tasks. Best price-performance for algorithm-heavy work.
O3 Mini
OpenAIOpenAI's reasoning model at lower cost. Strong at math, coding, and science tasks.
Gemini 2.5 Pro
GoogleGoogle's most capable model. Strong coding, multimodal understanding, and very competitive pricing.
Grok Code
xAIxAI's coding-specialized model. Optimized for code generation, debugging, and software engineering tasks.
GPT-4.1
OpenAIUpdated GPT-4 generation with improved instruction following and reduced hallucination. Better coding accuracy than GPT-4o.
Mistral Large 3
MistralLatest Mistral flagship model. Improved coding and multilingual capability over Large 2.
Cohere Command A
CohereCohere's newest model with strong agentic capabilities. Optimized for tool use and autonomous tasks.
GPT-4o
OpenAIOpenAI's flagship multimodal model. Strong coding and reasoning at competitive pricing.
Claude Sonnet 4
AnthropicAnthropic's balanced model for coding and general tasks. Best price-performance ratio in the Claude family.
Claude 3.5 Sonnet
AnthropicPrevious generation Sonnet. Still excellent for coding tasks at the same price point.
Qwen 3.6 Plus
QwenQwen's latest general-purpose model. Competitive with Claude Sonnet pricing.
Grok 3
xAIxAI's flagship model. Strong general-purpose capability with real-time knowledge access through X platform integration.
Grok 4
xAINext-generation xAI model with enhanced reasoning and coding capability. Competes with Claude Opus and o3 Pro tier.
Qwen 3 Max
QwenFlagship Qwen 3 model. Top-tier reasoning and coding, competitive with Claude Opus and GPT-4.1.
GLM-4-AllTools
Zhipu AIZhipu AI's most capable model with full tool use support. Code interpreter, web search, and image generation.
OpenAI o3
OpenAINext generation reasoning model. Improved coding and math over o1.
Claude Opus 4
AnthropicAnthropic's most powerful model. Best for complex reasoning and challenging coding tasks.
OpenAI o1
OpenAIReasoning model optimized for complex problem-solving. Excels at math, science, and advanced coding.
O1 Preview
OpenAIOpenAI's first reasoning model. Strong at complex problem solving but expensive.
OpenAI o3 Pro
OpenAITop-tier reasoning model combining o3's coding strength with extended compute. The most powerful OpenAI model for reasoning-heavy coding.