AI News

Tencent Hunyuan Hy4 on Artificial Analysis Cyber…

Tencent HunyuanUpdated Nov 13 17:03

AI summary

Artificial Analysis's evaluation shows that Tencent Hunyuan Hy4 scores 58% on the Artificial Analysis Cyber Index, ranking third, 1 point higher than DeepSeek V4.1 Flash 1017 (max), and behind Kimi K3.1 Pro (64%) and GPT-6 Sol (Daybreak Blue, max) (69%). On CWE-Bench-AA, which tests agents' ability to find and fix real software vulnerabilities, Hy4 ranks first with 76%, leading DeepSeek V4.1 Flash 1017 (max) by 6 points. Its API price is $0.834/$2.501 per 1M input/output tokens, with a cost per task of $0.92 and 64k output tokens per task.

Why read this

AI score 63

Artificial Analysis's evaluation provides Hy4's ranking, score, and cost per task on cybersecurity agent tasks, allowing horizontal comparison with DeepSeek, Kimi, and GPT-6.

Topics

Tags

Quoted post

Artificial Analysis

@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)

View original

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)

View original post

Body

#3 on the Artificial Analysis Cyber Index and #1 on CWE-Bench-AA 🎉🎉🎉

Source

Tencent Hunyuan