ericzakariasson· @ericzakariasson · X·· 15 天前AI 评分
Grok 4.7 模型卡公布多项基准分数较 4.6 提升
Grok 4.7 模型卡公布,多项基准分数较 4.6 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。
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!
media.x.ai/v1/website/4p7car…
来源:ericzakariasson · x.com