Artificial Analysis 评测显示，腾讯混元 Hy4 在 Cyber Index 上得分 58%，排名第三，落后 Kimi K3.1 Pro 的 64% 和 GPT-6 Sol 的 69%，领先 DeepSeek V4.1 Flash 1017（max）1 分。Hy4 在 CWE-Bench-AA 上以 76% 排名第一，领先 DeepSeek V4.1 Flash 1017（max）6 分；API 价格为每 1M 输入/输出 token 0.834/2.501 美元，单任务成本 0.92 美元，每任务输出 64k token。
#3 on the Artificial Analysis Cyber Index and #1 on CWE-Bench-AA 🎉🎉🎉
【引用 @ArtificialAnlys】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)
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)在 X 查看被引用的帖子
来源：Tencent Hy · x.com