Code Generation

Anthropic's most capable model, excelling at complex analysis, nuanced content creation, and advanced coding tasks. Features superior reasoning and the ability to work autonomously on extended tasks.

The best combination of performance and speed for efficient, high-throughput tasks. Excellent balance of intelligence and cost-effectiveness.

OpenAI's flagship multimodal model with advanced reasoning, vision, and audio capabilities. Fast and versatile for most tasks.

OpenAI's reasoning model designed to solve hard problems across science, coding, and math using chain-of-thought reasoning.

Fast, cost-efficient reasoning model excelling at STEM tasks. Offers adjustable reasoning effort levels.

Google's latest multimodal model with native tool use, code execution, and agentic capabilities. Fast and efficient.

Meta's latest open-source model offering performance comparable to Llama 3.1 405B at a fraction of the cost. Excellent for self-hosting.

Mistral's flagship model with top-tier reasoning, coding, and multilingual capabilities. Strong at complex tasks.

Specialized coding model trained on 80+ programming languages. Optimized for code completion and generation.

xAI's flagship model with strong reasoning and coding capabilities. Known for witty responses and real-time knowledge.

Meta's largest open-source model with 405 billion parameters. Competitive with leading closed models on benchmarks.

Efficient 12B model developed with NVIDIA. Drop-in replacement for Mistral 7B with improved performance.

Highly efficient 671B MoE model trained on 14.8T tokens. Achieves top benchmark scores at fraction of typical training cost.

Reasoning-focused model achieving strong performance on math and coding benchmarks through reinforcement learning.

Alibaba's flagship open-source model with strong coding and math capabilities. Supports 29 languages.

Specialized coding model available in sizes from 0.5B to 32B. State-of-the-art for open-source code models.