AI HOT (Curated Pool)Sep 22, 2026, 03:41 UTC+8

Grok 4.7 hits the frontier on agentic knowledge work, Coding Agent Index reaches 56

Artificial Analysis 评测 Grok 4.7：智能体知识工作跻身前沿，编码代理得分升至 56

Grok 4.7 scores 1657 Elo on AA-Briefcase, up 111 points from Grok 4.6, landing just behind Claude Opus 5 and Claude Fable 5.1 on long-horizon agentic knowledge work. Its Coding Agent Index jumps from 47 to 56, with DeepSWE rising from 65% to 73% and Terminal-Bench doubling to 33%. The gains come at a cost: 81k output tokens per task on average, nearly 3× what GPT-6 Astra uses. Pricing stays at $2/$6 per 1M input/output tokens, context window unchanged at 500k. Hallucination rate drops from 34% to 29%, accuracy is flat.

Why it matters: Grok 4.7 reaches the frontier tier on agentic knowledge work and coding agents, with 1657 Elo on AA-Briefcase and 56 on the Coding Agent Index — both directly comparable numbers. Not scored higher because gains outside agent tasks are incremental and the body is truncated, lea...

Read the original ↗Export Markdown

Take

This one's worth opening because Artificial Analysis lays out both the gains and the costs clearly. Grok 4.7 hit 1657 Elo on AA-Briefcase, up 111 points from Grok 4.6, with analytical quality jumping from 1690 to 1994 — right up there with Claude Opus 5 and Fable 5.1. The Coding Agent Index climbed from 47 to 56, Terminal-Bench doubled to 33%, and DeepSWE went from 65% to 73%.

The catch: it burns way more tokens. Average output per task is 81k tokens, more than double Grok 4.6 and nearly triple GPT-6 Astra. Pricing stayed at $2/$6 per million tokens, but real task cost will climb because of the volume. Presentation quality actually slipped from 1519 to 1499, so the model got better at analysis but slightly worse at packaging results. Hallucination rate dropped from 34% to 29%, accuracy flat.

My take: Grok 4.7 caught up to the frontier by thinking longer and writing more. It fits knowledge-work tasks where analytical depth matters and token cost isn't the main constraint. But if you need concise output or tight cost control, GPT-6 Astra does comparable work with 27k tokens — that gap is still significant.

Source: AI HOT (Curated Pool) · artificialanalysis.ai
Published: Sep 22, 2026, 03:41 UTC+8 · 8 days ago