跳到正文
eric zakariasson· @ericzakariasson · X·· 15 天前AI 评分64
AI 导读

Grok 4.7 模型卡公布,多项基准较 4.6 有明显提升。Terminal-Bench 从 20.3% 升至 38.0%,SWE-Marathon 从 31.9% 升至 46.0%,HealthBench Pro 从 48.5% 升至 56.7%,Legal Agent 从 15.8% 升至 19.6%,EEBench 从 60.0% 升至 66.0%,价格与 4.6 相同。模型卡见 https://media.x.ai/v1/website/4p7card-5eccc980.pdf

正文

and here’s the grok 4.7 model card. a few jumps vs 4.6 that stood out:

- Terminal-Bench: 20.3% → 38.0%
- SWE-Marathon: 31.9% → 46.0%
- HealthBench Pro: 48.5% → 56.7%
- Legal Agent: 15.8% → 19.6%
- EEBench: 60.0% → 66.0%

for the same price as 4.6!

https://media.x.ai/v1/website/4p7card-5eccc980.pdf

来源:eric zakariasson · x.com