# Grok 4.5 每美元智能表现亮眼

- 来源：Rohan Paul (@rohanpaul_ai)
- 发布时间：2026-07-18 11:52
- AIHOT 分数：41
- AIHOT 链接：https://aihot.virxact.com/items/cmrpucie205l1bisrxcz1xy3w
- 原文链接：https://x.com/rohanpaul_ai/status/2078327046191907120

## AI 摘要

Grok 4.5 在 Artificial Analysis 的 Intelligence Index 任务中每项仅需 $0.31，成本约为 Claude Fable 5 的 1/9。它在 FrontierSWE 上 token 消耗比 Fable 5 少近 6 倍，仍保持接近顶尖排名。Elon Musk 称，综合考虑速度和成本，Grok 4.5 可算第一。

## 正文

On intelligence per dollar basis Grok 4.5 looking brilliant.

AI. At $0.31 per Intelligence Index task (of Artificial Analysis), it delivers near-frontier performance at roughly 1/9 the cost of Claude Fable 5, 1/6 the cost of Claude Opus 4.8, and about 1/3 the cost of GPT-5.6 Sol or Kimi K3.

That's more relevant with the token-consumption data. Grok 4.5 uses nearly 6X fewer tokens than Fable 5 while still being near the top of the ranking, onFrontierSWE.

For many real-life AI applications this is better than a small lead on a benchmark.

Lower cost per completed task means cheaper agents, higher usage limits, faster testing and better margins at scale.

The frontier model race must shift from "raw intelligence" to "efficient intelligence".

### 引用推文

> Elon Musk：Grok 4.5 is arguably #1 when taking speed and cost into account