LLM Capability Leaderboard

Premium model with strong writing, code review, and agentic workflow behavior.

OpenAI frontier work model for complex real-world tasks, agentic coding, research, data analysis, and cross-tool execution.

Frontier general model for complex reasoning, coding, tool use, and professional writing.

General model with strong long-context, multimodal, and reasoning capability.

Thinking model for complex Q&A and fresh-information workflows.

Z.AI flagship model for long-horizon agent tasks, real-world engineering delivery, coding, and complex reasoning.

Z.AI GLM-5 foundation model for general reasoning, writing, coding, and agentic engineering workflows.

General model with strong long-context and Chinese-language performance.

Coding-optimized model for repository-scale editing, testing, and debugging.

DeepSeek next-generation V4 family model for long-context work, coding, math reasoning, and cost-efficient production APIs.

Z.AI GLM-4.6 improves real-world coding, long-context processing, reasoning, search, writing, and agentic applications.

Balanced multilingual and coding model with broad API availability.

European model for enterprise API, coding, and multilingual workloads.

Stable model for Chinese, writing, and general knowledge tasks.

Low-latency DeepSeek V4 variant for high-throughput, cost-sensitive, and real-time product scenarios.

Large open-weight model for self-hosted enterprise and research workflows.

Open-weight reasoning model focused on math, coding, and cost-efficient deployment.

Open-weight MoE model for self-hosting and cost-sensitive inference.