Grok 4.6 reaches frontier benchmark scores at lower token prices

Grok 4.6 has moved into the top tier of public benchmark comparisons while keeping token prices well below several frontier rivals, according to The Decoder’s summary of Artificial Analysis results.

The report says xAI’s model scored 61 on the Artificial Analysis Intelligence Index, tying OpenAI’s GPT-5.6 Sol and trailing only Anthropic’s Claude Opus 5 and Claude Fable 5. It also highlights stronger performance on agentic tasks, where models carry out multi-step workflows on a computer.

Benchmarks are not the same as everyday reliability, but the pricing detail is important for developers choosing models for high-volume work. The report lists Grok 4.6 at $2 per million input tokens and $6 per million output tokens, a level that could make frontier-like performance more accessible for agent systems and coding workflows.

The useful question is how the model behaves outside benchmark suites. For now, the news adds another serious option in a market where capability, latency, tooling, and cost all shape adoption.