Grok 4.6

Grok 4.6 debuts with strong performance across core benchmarks

Grok 4.6 enters the benchmark landscape as xAI's first evaluated model in this tracking window, establishing baseline performance metrics across multiple domains. The model demonstrates particularly strong performance in mathematical reasoning, achieving 89.4% on MATH-500 and 93.8% on GSM8K, placing it competitively among frontier models. Coding capabilities are robust with 86.5% on HumanEval and 79.6% on LiveCodeBench, indicating solid software engineering capabilities. Academic knowledge shows strength at 88.6% on MMLU-Pro, though GPQA performance at 56.4% suggests room for improvement in graduate-level science questions. Multimodal capabilities are present with 74.3% on MMMU, establishing vision-language integration. The model supports JSON output, tool use, and reasoning modes, providing developers with flexible interaction patterns. With a 128K token context window, Grok 4.6 handles substantial documents and conversations. As a baseline entry, these metrics establish xAI's position in the competitive landscape, showing particular strength in mathematical and coding tasks while maintaining competent performance across general knowledge domains. Future benchmark windows will reveal how the model evolves relative to this initial showing.