挑選 AI 模型協助找出並修補軟體漏洞時,除了看分數,也得考慮花費和輸出的長度。
- Artificial Analysis 評測 Tencent 的 Hy4,在自家 Cyber Index 得 58%,排名第 3。
- 在測試 AI 助理找出並修補真實軟體漏洞的 CWE-Bench-AA 得 76%,排名第 1。每項任務成本是 $0.92,輸出 64k tokens。這些數字讓人能同時比較漏洞測試表現與成本,但只反映這篇評測採用的測試結果。
AI 伴隨問答
針對這篇報導有疑問?可直接點選快捷問題或向 AI 追問背景脈絡與技術細節:
Hy4 在漏洞修補測試中的表現、每項任務成本與輸出 token 數,可一併用來比較不同模型的能力和花費。
Tencent's Hy4 ranks #3 on the Artificial Analysis Cyber Index and #1 on CWE-Bench-AA
@TencentHunyuan's Hy4 scores 58% on the Artificial Analysis Cyber Index, 1 point ahead of DeepSeek V4.1 Flash 1017 (max). It trails Kimi K3.1 Pro (64%) and the trusted-access GPT-6 Sol (Daybreak Blue, max) (69%). API pricing is $0.834/$2.501 per 1M input/output tokens.
Key results:
➤ #1 on CWE-Bench-AA (76%). Hy4 leads DeepSeek V4.1 Flash 1017 (max) by 6 points on our implementation of @CollinearAI's CWE-bench v1, which tests agents' ability to find and fix real software vulnerabilities
➤ Strong capability for the cost. At $0.92 per task, Hy4 sits on the Capability vs. Cost Pareto frontier. It scores 2 points above Grok 4.7 (xhigh) at 1/11th the cost and 1 point above DeepSeek V4.1 Flash 1017 (max) at 2x the cost
➤ Fewer output tokens than peers. Hy4 uses 64k output tokens per task: 43% fewer than DeepSeek V4.1 Flash 1017 (max) and 37% fewer than Grok 4.7 (xhigh), but 49% more than Kimi K3.1 Pro and 56% more than GPT-6 Sol (Daybreak Blue, max)